ledger: arXiv cs.AI most-recent 20 submissions (2026-10-28) extraction table + reverify gate
This commit is contained in:
ledger committed
1 parent
f7844b11ab
commit
ef601829df
7 files changed
+2056
No files matched your search
@@ -0,0 +1,7 @@
|
||||
#!/usr/bin/env bash
|
||||
# CHECK -- arXiv cs.AI most-recent table (20 rows), pinned to raw_api.xml.
|
||||
# Re-derives the TSV/JSON/MD tables from raw_api.xml and diffs against the
|
||||
# committed files. Exit 0 only on an exact match.
|
||||
set -u
|
||||
cd "$(dirname "${BASH_SOURCE[0]}")" || exit 1
|
||||
exec python3 reverify.py verify
|
||||
@@ -0,0 +1,22 @@
|
||||
# arXiv cs.AI — most recent 20 submissions (2026-10-28)
|
||||
|
||||
Extraction + re-verification gate. 20 latest arXiv `cs.AI` submissions fetched
|
||||
from the arXiv API on 2026-10-28, re-derived and diffed byte-for-byte from the
|
||||
pinned `raw_api.xml` snapshot.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Contents |
|
||||
| --- | --- |
|
||||
| `raw_api.xml` | pinned arXiv API Atom feed (source of truth; `updated` = 2026-10-28T02:33:55Z) |
|
||||
| `arxiv_csai_recent.tsv` | tab-separated table (rank, arxiv_id, title, authors, published, updated, categories, primary_category, abstract) |
|
||||
| `arxiv_csai_recent.json` | same rows as JSON |
|
||||
| `arxiv_csai_recent.md` | markdown table (20 data rows) |
|
||||
| `reverify.py` | emit/verify gate: `python3 reverify.py verify` exits 0 only on exact match |
|
||||
| `CHECK` | verdict line: run `python3 reverify.py verify` |
|
||||
|
||||
## Evidence
|
||||
|
||||
- Fetch command: `curl -s "https://export.arxiv.org/api/query?search_query=cat:cs.AI&sortBy=submittedDate&sortOrder=descending&max_results=20"`
|
||||
- API `<updated>` / fetch timestamp: `2026-10-28T02:33:55Z`
|
||||
- `<id>` values are pinned via `raw_api.xml`; no network fetch inside the gate.
|
||||
@@ -0,0 +1,222 @@
|
||||
[
|
||||
{
|
||||
"arxiv_id": "2610.37668",
|
||||
"title": "Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction",
|
||||
"authors": "Prakhar Kaushik; Soumava Paul; Alan Yuille",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.CV; cs.AI; cs.GR; cs.LG",
|
||||
"primary_category": "cs.CV",
|
||||
"abstract": "Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resource-constrained settings. We introduce Hexels: novel planar hexagonal surface elements with a first-order spatial color field for ef",
|
||||
"rank": 1
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37666",
|
||||
"title": "ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning",
|
||||
"authors": "Chaehyun Kim; Chi-Pin Huang; Jisoo Kim; Min-Hung Chen; Yu-Chiang Frank Wang; Seungryong Kim; Fu-En Yang",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.RO; cs.AI; cs.CV",
|
||||
"primary_category": "cs.RO",
|
||||
"abstract": "Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the diversity and coverage of action-labeled robot demonstrations. Human videos provide much broader behavioral and environmental experience, while learning fro",
|
||||
"rank": 2
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37656",
|
||||
"title": "Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops",
|
||||
"authors": "Aakash Sarkar; Ananya Mukherjee; Motoshige Sato",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.LG; cs.AI; physics.comp-ph",
|
||||
"primary_category": "cs.LG",
|
||||
"abstract": "Relations compose through the entity they share - Alice is Bob's mother and Bob is Carol's father, so Alice is Carol's grandmother - and the order matters, since a father's mother is not a mother's father; verifying a composed relation means closing the loop. We show that if each entity's coordinate",
|
||||
"rank": 3
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37655",
|
||||
"title": "KPPax: preprocess differentiable kinetic ODE for machine learning in atmospheric chemistry",
|
||||
"authors": "Wenqing Peng; Michael Boy; Zhi-Song Liu",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.AI",
|
||||
"primary_category": "cs.AI",
|
||||
"abstract": "Atmospheric chemical mechanisms are commonly distributed in the language of the Kinetic PreProcessor (KPP), which generates efficient Fortran or C code but does not fit into the differentiable programming frameworks in which machine-learning models are developed. We present KPPax, a kinetic preproce",
|
||||
"rank": 4
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37649",
|
||||
"title": "Can LLMs Uncover Hidden Physical Laws through Free Exploration?",
|
||||
"authors": "Zhen Yang; Wen Wang; Xander Xu; Ying-Cong Chen",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.CL; cs.AI; cs.MA",
|
||||
"primary_category": "cs.CL",
|
||||
"abstract": "Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notice unexpected behavior, such as heavier objects falling more slowly, and discover the law through experiments without bei",
|
||||
"rank": 5
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37647",
|
||||
"title": "MuonGS: Pretraining LLMs with Relaxed Weight-Norm Control",
|
||||
"authors": "Athanasios Glentis; Dawei Li; Mingyi Hong",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.LG; cs.AI; math.OC",
|
||||
"primary_category": "cs.LG",
|
||||
"abstract": "Weight decay and explicit weight-norm constraints improve optimizer performance in language model pretraining, yet a unified understanding of why such control helps and how much is needed remains incomplete. We analyze norm control in Muon over the entire training trajectory using the \\emph{accumula",
|
||||
"rank": 6
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37631",
|
||||
"title": "What Improves During Pretraining? Tracking Knowledge Acquisition with Point-in-Time Models",
|
||||
"authors": "Chang Su; Bin Wu; Emine Yilmaz; Yao Lu",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.AI",
|
||||
"primary_category": "cs.AI",
|
||||
"abstract": "Language models pretrained on web corpora collected over multiple years learn both general and domain-specific knowledge. How these different kinds of knowledge are learned as pretraining progresses remains unclear. Recent point-in-time models trained on web snapshots from different years provide a ",
|
||||
"rank": 7
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37624",
|
||||
"title": "Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions",
|
||||
"authors": "Anouar Imel; Imad Charradi; Abderrahman Sghir; Khalil El Khammar",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.AI; cs.CL; cs.MA; cs.SI",
|
||||
"primary_category": "cs.AI",
|
||||
"abstract": "When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claims relevant to the decision criteria. On hidden-profile tasks both look attractive, because how widely a fact is held is ",
|
||||
"rank": 8
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37613",
|
||||
"title": "VideoLVR: Latent Visual Reasoning over Grounded Video Evidence",
|
||||
"authors": "Shilong Li; Xingyuan Bu; Hao Shi; Yun Xing; Weixin Feng; Qiangpeng Yang; Shilei Wen",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.CV; cs.AI",
|
||||
"primary_category": "cs.CV",
|
||||
"abstract": "Chain-of-thought reasoning has substantially advanced video understanding in multimodal large language models (MLLMs). However, language-based reasoning traces do not provide a reliable mechanism for models to revisit relevant visual evidence, leading to visual forgetting and impairing their ability",
|
||||
"rank": 9
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37605",
|
||||
"title": "Beyond Answer Changes: Matched Same-Class Controls for Local Audio Evidence",
|
||||
"authors": "Yunuo Wang; Maoyuan Chen; Yuanjin Huang; Xing Liu",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.SD; cs.AI",
|
||||
"primary_category": "cs.SD",
|
||||
"abstract": "For audio-language models, an answer change after a local sound-event edit can reflect a response to the event's class, sensitivity to waveform rewriting, or both. We compare matched same-class and different-class replacements of a queried event. Both use the same interval, level estimate, donor fit",
|
||||
"rank": 10
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37599",
|
||||
"title": "MoI-Bench: A Benchmark for Image Generation and Editing on Mobile Devices",
|
||||
"authors": "Kailai Feng; Haoxiang Rao; Yuxiang Wei; Bo Chen; Junsong Li; Yang Pan; Chengkun Cai; Jagmohan Chauhan",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.CV; cs.AI",
|
||||
"primary_category": "cs.CV",
|
||||
"abstract": "Developing on-device image models requires considering practical user needs, task types and device resource constraints. However, existing benchmarks provide limited guidance on identifying capability gaps between on-device models and server-side models. We introduce MoI-Bench, a benchmark grounded ",
|
||||
"rank": 11
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37598",
|
||||
"title": "GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting",
|
||||
"authors": "Joseph Natter; Long Vu; Yifan Zhang; Bobin Deng; Kun Suo; Rui Wu",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.LG; cs.AI; cs.NE",
|
||||
"primary_category": "cs.LG",
|
||||
"abstract": "Traffic forecasting requires modeling complex temporal dynamics and the spatial dependencies imposed by road topology. Supervised graph-based models achieve strong performance, but are often trained for a particular dataset and sensor graph, making deployment to new or evolving networks costly. Prio",
|
||||
"rank": 12
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37588",
|
||||
"title": "Understanding the limits of latent world models",
|
||||
"authors": "Rodrigo Gonzalez Laiz; Steffen Schneider",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.LG; cs.AI",
|
||||
"primary_category": "cs.LG",
|
||||
"abstract": "World models are widely proposed as core components for enabling agents to reason over long temporal and spatial horizons. Yet current evaluations often emphasize task performance while providing limited insight into whether learned world models acquire predictive latent dynamics that reflect the un",
|
||||
"rank": 13
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37585",
|
||||
"title": "Timestral",
|
||||
"authors": "Adrien Petralia; Alexandre Gavaudan; Artjom Joosen; Etienne Goffinet; Richard Kurle; Yassine El Ouahidi; Yassir Bendou; Abdelaziz Bounhar; Abhijeet Somani; Aditi Kabra; Adrian Valente; Adrien Sadé; Ahmed Djermani; Alan Jeffares; Albert Jiang; Alberto Bietti; Aleksandr Timashov; Alexandre Cahill; Alexandre Laval; Alexandre Sablayrolles; Alexandros Sanchez Vassopoulos; Amélie Héliou; Amos You; André Jonasson; Andreas Fürst; Andrew Bai; Andrew Ehrenberg; Andrew Zhao; Andy Lo; Angele Lenglemetz; Anmol Agarwal; Antonia Calvi; Arata Suzuki; Arjun Majumdar; Arthur Fournier; Ashwani Kumar; Augustin Lombard; Avinash Sooriyarachchi; Aylin Guliz Akkus; Aysenur Karaduman; Baptiste Bout; Baptiste Rozière; Barna Pásztor; Baudouin De Monicault; Benjamin Holzschuh; Benjamin Tibi; Benno Stein; Bernhard Stadlbauer; Bhargavi Bhaskar; Binbing Hou; Błażej Osiński; Boris van Breugel; Camille Le Scao; Chaoran Yu; Charlotte Cronjäger; Chen-Yo Sun; Chris Bamford; Christian Wallenwein; Christophe Renaudin; Clémence Lanfranchi; Colin Bonatti; Corentin Barreau; Corentin Sautier; Cristiana-Diana Diaconu; Cyprien Courtot; Daniel Lopes; Daniel Marczak; Darius Dabert; Diego de las Casas; Dominik Nuss; Dylan Rubini; Dzmitry Soupel; Elizaveta Demyanenko; Elliot Chane-Sane; Emilien Fugier; Emmanuel Gottlob; Erik Aas; Etienne Duchesne; Fabian Paischer; Fabian Schlager; Faruk Ahmed; Federico Baldassarre; Félix Rosseeuw; Filip Szatkowski; Filippo Vicentini; Florian Wiesner; Gabrielle Berrada; Gaëtan Ecrepont; Gaspard Blanchet; Gaspard Donada-Vidal; Gaurav Mahajan; Gauthier Guinet; Genevieve Hayes; Georgii Novikov; Georgios Christoglou; Giada Pistilli; Gonzague de Carpentier; Graeme Nail; Guillaume Breton; Guillaume Kunsch; Guillaume Lample; Guillaume Martin; Guillaume Raille; Guillaume Richard; Guillem Simeon; Gunjan Dhanuka; Gunshi Gupta; Hamza Senhaji Rhazi; Han Zhou; Hédi Hadiji; Himanshu Jaju; Hope McGovern; Hubert de Parseval; Hugo Cisneros; Hugo Germain; Hugo Thimonier; Hugo Venturini; Hyeonju Lee; Hyunwoo Oh; Iliass Lasri; Ilyas Oulkadda; Jacques Sun; Jan Ludziejewski; Jason Rute; Jean de Becdelièvre; Jean Quentin; Jean-Malo Delignon; Jessica Chudnovsky; Jianchao Li; Jie Zhang; Jin Bin Ou; Joachim Studnia; Joep Barmentlo; Johannes Brandstetter; John Harvill; Jonas Amar; Jonas Schweizer; Jonathan Roberts; Joséphine Delas; Josselin Somerville; Jules Depersin; Julien Denize; Julien Tauran; Julien Verlaguet; Kartik Khandelwal; Khyathi Raghavi Chandu; Kilian Tep; Konstantin Mishchenko; Kris Szczepaniak; Kush Jain; Larissa Laich; Laura Calem; Laurence Aitchison; Laurent Callot; Laurent Fainsin; Léo Cotteleer; Léonard Blier; Loïc Chadoutaud; Loïck Chambon; Lorenzo Proietti; Louis Faucon; Louis Martin; Louis Serrano; Lu Li; Luc Boudier; Lucas Fernandes Martins; Lucas Mebille; Lucile Saulnier; Ludovic Ho Fuh; Luis Montero; Łukasz Borchmann; Maarten Buyl; Malik Hassan Raza; Manon Chossegros; Marcin Możejko; Margaret Jennings; Markus Hennerbichler; Martin Alexandre; Mathieu Poirée; Mathieu Schmitt; Mathilde Guillaumin; Mathis Felardos; Matthieu André; Matthieu Dinot; Matthieu Futeral; Maurits Bleeker; Mauro Comi; Max Mynter; Maxim Berman; Maxime Darrin; Maxime Langelier; Maxime Louis; Maximilian Augustin; Maximilian Müller; Mehdi Bouaziz; Melina Jingting Laimon; Mert Unsal; Mia Chiquier; Michael Pilcer; Michał Pietruszka; Michał Zając; Mickaël Seznec; Mikhail Biriuchinskii; Minh-Quang Pham; Minwoo Kang; Mircea Lica; Morgane Rivière; Namit Katariya; Natasha Ørregaard Klingenbrunn; Nathan Bout; Nathan Grinsztajn; Nathan Simpson; Neeraj Aggarwal; Neil Ashton; Neil Mallinar; Nick Bührer; Nicolas Moreau; Nicolò Lucchesi; Ola Mysiak; Oliver Leicht; Olivier Bousquet; Olivier Koch; Parag Jain; Patricia Wang; Patrick Blies; Patrick von Platen; Patryk Saffer; Paul Jacob; Paul Teiletche; Paul Wambergue; Paula Kurylowicz; Pavan Kumar Reddy; Pavel Kuksa; Philippe Formont; Philippe Pinel; Philomène Chagniot; Pierre Glandon; Pierre Stock; Pierre-André Savalle; Piotr Miłoś; Poojan Shah; Prateek Gupta; Pravesh Agrawal; Pui Ki Chan; Quentin Desreumaux; Quentin Selle; Quentin Torroba; Quentin Wargnier; Quercus Hernandez; Ram Ramrakhya; Randall Isenhour; Ranjit Parva; Raphaël Balouka; Raphaël Rialland; Raul Perez Pelaez; Reinhard Sonnleitner; Remi Delacourt; Rishi Shah; Rob Romijnders; Rohan Shah; Rohin Arora; Romain Sauvestre; Roman Soletskyi; Ronan Riochet; Rosalie Millner; Rupert Menneer; Sagar Vaze; Samuel Barry; Samuel Belkadi; Samuel Humeau; Samuele Papa; Sanchit Gandhi; Sandeep Cranganore; Sandeep Subramanian; Sarthak Mittal; Saskia Adaime; Scott Matthews; Sean Cha; Sebastian Kaltenbach; Seungjae Jung; Shashwat Verma; Sherif Waly; Shrimai Prabhumoye; Siddhant Waghjale; Siddharth Gandhi; Simon Lepage; Simon Sorg; Soham Ghosh; Sophie Marbach; Srijan Mishra; Stanislas Lange; Steve Hong; Sumukh Aithal; Szymon Antoniak; Tarun Kumar Vangani; Teddy Turquet; Teven Le Scao; Théo Cachet; Thibaut Lavril; Thomas ChaLine truncated
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.AI",
|
||||
"primary_category": "cs.AI",
|
||||
"abstract": "We introduce Timestral, a family of four time series foundation models for probabilistic forecasting, with 5M, 28M, 123M, and 209M parameters. Timestral sets a new state of the art on GIFT-Eval, TIME, and fev-bench, where Timestral-209M and Timestral-123M take the top two places on every metric. We ",
|
||||
"rank": 14
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37584",
|
||||
"title": "REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation",
|
||||
"authors": "Yuxi Huang; Silin Zhou; Chenhao Wang; Zihan Li; Gangming Guo; Pei Ke; Shen Gao; Shuo Shang",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.IR; cs.AI",
|
||||
"primary_category": "cs.IR",
|
||||
"abstract": "Personalized recommendation depends on learning semantic and collaborative relations among items from online content and user interactions. Generative recommendation (GR) offers a promising paradigm by autoregressively generating discrete semantic IDs (SIDs) of items. However, randomly initialized S",
|
||||
"rank": 15
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37571",
|
||||
"title": "TeamGym: A Gym for Team Decision-Making by AI Agents with Distributed Information",
|
||||
"authors": "Chanwoo Park; Jaywoong Jeong; Zachary Wojtowicz; Yubin Kim; Taekyun Lee; Kaiqing Zhang; Asuman Ozdaglar",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.AI",
|
||||
"primary_category": "cs.AI",
|
||||
"abstract": "Many real-world decisions require teams to integrate information distributed across participants. Yet AI agents are still primarily trained and benchmarked in isolation. We introduce TeamGym, an environment for evaluating and training language model-based agents on team decision-making problems cons",
|
||||
"rank": 16
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37567",
|
||||
"title": "Gym-Anything-RT: Scaling Real-Time Environments for Vision-Language Agents",
|
||||
"authors": "Pranjal Aggarwal; Sean Welleck",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.LG; cs.AI",
|
||||
"primary_category": "cs.LG",
|
||||
"abstract": "AI agents have made substantial progress in domains where they have a non-trivial amount of time to deliberate between actions, such as mathematics, software engineering, and performing tasks on desktop applications. It is less clear how such models fare in settings that demand real-time interaction",
|
||||
"rank": 17
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37561",
|
||||
"title": "When uncertainty quantification fails: structural vulnerabilities and corrections for selective prediction under clinical class imbalance",
|
||||
"authors": "Walter Endrizzi; Flavio Ragni; Raffaele Marchesi; Stefano Bovo; Monica Moroni; Giuseppe Jurman; Venet Osmani",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.LG; cs.AI",
|
||||
"primary_category": "cs.LG",
|
||||
"abstract": "Background. Selective prediction systems improve the safety of clinical artificial intelligence by deferring ambiguous cases to human experts while automating high-confidence decisions. However, this safety mechanism relies entirely on the premise that uncertainty scores accurately reflect clinical ",
|
||||
"rank": 18
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37550",
|
||||
"title": "Kinematic Constraint-Referenced Evaluation for Articulated Object Manipulation",
|
||||
"authors": "Baptiste Bonin; Caro Strickland; Audrey Durand",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.RO; cs.AI",
|
||||
"primary_category": "cs.RO",
|
||||
"abstract": "Manipulation policies are evaluated predominantly by binary task success, which cannot tell whether the commanded gesture is the one the object's kinematics admit. We introduce Constraint-Referenced Strategy (CRS), which projects the commanded end-effector twist onto the object's joint axis, separat",
|
||||
"rank": 19
|
||||
},
|
||||
{
|
||||
"arxiv_id": "2610.37547",
|
||||
"title": "When, Where, and What to Correct: Human-Guided Adaptive Residual Correction for Robot Policies",
|
||||
"authors": "Anukriti Singh; Maxime Caniot; Pratap Tokekar; Firas Abi-Farraj",
|
||||
"published": "2026-10-27",
|
||||
"updated": "2026-10-27",
|
||||
"categories": "cs.RO; cs.AI",
|
||||
"primary_category": "cs.RO",
|
||||
"abstract": "Imitation policies that reliably execute most of a manipulation trajectory can still fail in localized regions requiring last-mile precision. Updating the full policy or exploring residual actions everywhere treats this local failure as a global learning problem. We introduce Adaptive Residual Corre",
|
||||
"rank": 20
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,26 @@
|
||||
# arXiv cs.AI — most recent 20 submissions (fetched 2026-10-28)
|
||||
|
||||
Source: `raw_api.xml` (API: cat:cs.AI, sortBy=submittedDate, sortOrder=descending, max_results=20)
|
||||
|
||||
| Rank | arXiv | Title | Authors | Published | Updated | Categories | Primary | Abstract (first 50 chars) |
|
||||
|---:|---|---|---|---|---|---|---|---|
|
||||
| 1 | 2610.37668 | Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction | Prakhar Kaushik; Soumava Paul; Alan Yuille | 2026-10-27 | 2026-10-27 | cs.CV; cs.AI; cs.GR; cs.LG | cs.CV | Novel view synthesis and 3D reconstruction have ad… |
|
||||
| 2 | 2610.37666 | ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning | Chaehyun Kim; Chi-Pin Huang; Jisoo Kim; Min-Hung Chen; Yu-Chiang Frank Wang; Seungryong Kim; Fu-En Yang | 2026-10-27 | 2026-10-27 | cs.RO; cs.AI; cs.CV | cs.RO | Vision-Language-Action (VLA) models have made subs… |
|
||||
| 3 | 2610.37656 | Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops | Aakash Sarkar; Ananya Mukherjee; Motoshige Sato | 2026-10-27 | 2026-10-27 | cs.LG; cs.AI; physics.comp-ph | cs.LG | Relations compose through the entity they share - … |
|
||||
| 4 | 2610.37655 | KPPax: preprocess differentiable kinetic ODE for machine learning in atmospheric chemistry | Wenqing Peng; Michael Boy; Zhi-Song Liu | 2026-10-27 | 2026-10-27 | cs.AI | cs.AI | Atmospheric chemical mechanisms are commonly distr… |
|
||||
| 5 | 2610.37649 | Can LLMs Uncover Hidden Physical Laws through Free Exploration? | Zhen Yang; Wen Wang; Xander Xu; Ying-Cong Chen | 2026-10-27 | 2026-10-27 | cs.CL; cs.AI; cs.MA | cs.CL | Scientific discovery often begins with an unexpect… |
|
||||
| 6 | 2610.37647 | MuonGS: Pretraining LLMs with Relaxed Weight-Norm Control | Athanasios Glentis; Dawei Li; Mingyi Hong | 2026-10-27 | 2026-10-27 | cs.LG; cs.AI; math.OC | cs.LG | Weight decay and explicit weight-norm constraints … |
|
||||
| 7 | 2610.37631 | What Improves During Pretraining? Tracking Knowledge Acquisition with Point-in-Time Models | Chang Su; Bin Wu; Emine Yilmaz; Yao Lu | 2026-10-27 | 2026-10-27 | cs.AI | cs.AI | Language models pretrained on web corpora collecte… |
|
||||
| 8 | 2610.37624 | Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions | Anouar Imel; Imad Charradi; Abderrahman Sghir; Khalil El Khammar | 2026-10-27 | 2026-10-27 | cs.AI; cs.CL; cs.MA; cs.SI | cs.AI | When an LLM group's discussion is compressed into … |
|
||||
| 9 | 2610.37613 | VideoLVR: Latent Visual Reasoning over Grounded Video Evidence | Shilong Li; Xingyuan Bu; Hao Shi; Yun Xing; Weixin Feng; Qiangpeng Yang; Shilei Wen | 2026-10-27 | 2026-10-27 | cs.CV; cs.AI | cs.CV | Chain-of-thought reasoning has substantially advan… |
|
||||
| 10 | 2610.37605 | Beyond Answer Changes: Matched Same-Class Controls for Local Audio Evidence | Yunuo Wang; Maoyuan Chen; Yuanjin Huang; Xing Liu | 2026-10-27 | 2026-10-27 | cs.SD; cs.AI | cs.SD | For audio-language models, an answer change after … |
|
||||
| 11 | 2610.37599 | MoI-Bench: A Benchmark for Image Generation and Editing on Mobile Devices | Kailai Feng; Haoxiang Rao; Yuxiang Wei; Bo Chen; Junsong Li; Yang Pan; Chengkun Cai; Jagmohan Chauhan | 2026-10-27 | 2026-10-27 | cs.CV; cs.AI | cs.CV | Developing on-device image models requires conside… |
|
||||
| 12 | 2610.37598 | GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting | Joseph Natter; Long Vu; Yifan Zhang; Bobin Deng; Kun Suo; Rui Wu | 2026-10-27 | 2026-10-27 | cs.LG; cs.AI; cs.NE | cs.LG | Traffic forecasting requires modeling complex temp… |
|
||||
| 13 | 2610.37588 | Understanding the limits of latent world models | Rodrigo Gonzalez Laiz; Steffen Schneider | 2026-10-27 | 2026-10-27 | cs.LG; cs.AI | cs.LG | World models are widely proposed as core component… |
|
||||
| 14 | 2610.37585 | Timestral | Adrien Petralia; Alexandre Gavaudan; Artjom Joosen; Etienne Goffinet; Richard Kurle; Yassine El Ouahidi; Yassir Bendou; Abdelaziz Bounhar; Abhijeet Somani; Aditi Kabra; Adrian Valente; Adrien Sadé; Ahmed Djermani; Alan Jeffares; Albert Jiang; Alberto Bietti; Aleksandr Timashov; Alexandre Cahill; Alexandre Laval; Alexandre Sablayrolles; Alexandros Sanchez Vassopoulos; Amélie Héliou; Amos You; André Jonasson; Andreas Fürst; Andrew Bai; Andrew Ehrenberg; Andrew Zhao; Andy Lo; Angele Lenglemetz; Anmol Agarwal; Antonia Calvi; Arata Suzuki; Arjun Majumdar; Arthur Fournier; Ashwani Kumar; Augustin Lombard; Avinash Sooriyarachchi; Aylin Guliz Akkus; Aysenur Karaduman; Baptiste Bout; Baptiste Rozière; Barna Pásztor; Baudouin De Monicault; Benjamin Holzschuh; Benjamin Tibi; Benno Stein; Bernhard Stadlbauer; Bhargavi Bhaskar; Binbing Hou; Błażej Osiński; Boris van Breugel; Camille Le Scao; Chaoran Yu; Charlotte Cronjäger; Chen-Yo Sun; Chris Bamford; Christian Wallenwein; Christophe Renaudin; Clémence Lanfranchi; Colin Bonatti; Corentin Barreau; Corentin Sautier; Cristiana-Diana Diaconu; Cyprien Courtot; Daniel Lopes; Daniel Marczak; Darius Dabert; Diego de las Casas; Dominik Nuss; Dylan Rubini; Dzmitry Soupel; Elizaveta Demyanenko; Elliot Chane-Sane; Emilien Fugier; Emmanuel Gottlob; Erik Aas; Etienne Duchesne; Fabian Paischer; Fabian Schlager; Faruk Ahmed; Federico Baldassarre; Félix Rosseeuw; Filip Szatkowski; Filippo Vicentini; Florian Wiesner; Gabrielle Berrada; Gaëtan Ecrepont; Gaspard Blanchet; Gaspard Donada-Vidal; Gaurav Mahajan; Gauthier Guinet; Genevieve Hayes; Georgii Novikov; Georgios Christoglou; Giada Pistilli; Gonzague de Carpentier; Graeme Nail; Guillaume Breton; Guillaume Kunsch; Guillaume Lample; Guillaume Martin; Guillaume Raille; Guillaume Richard; Guillem Simeon; Gunjan Dhanuka; Gunshi Gupta; Hamza Senhaji Rhazi; Han Zhou; Hédi Hadiji; Himanshu Jaju; Hope McGovern; Hubert de Parseval; Hugo Cisneros; Hugo Germain; Hugo Thimonier; Hugo Venturini; Hyeonju Lee; Hyunwoo Oh; Iliass Lasri; Ilyas Oulkadda; Jacques Sun; Jan Ludziejewski; Jason Rute; Jean de Becdelièvre; Jean Quentin; Jean-Malo Delignon; Jessica Chudnovsky; Jianchao Li; Jie Zhang; Jin Bin Ou; Joachim Studnia; Joep Barmentlo; Johannes Brandstetter; John Harvill; Jonas Amar; Jonas Schweizer; Jonathan Roberts; Joséphine Delas; Josselin Somerville; Jules Depersin; Julien Denize; Julien Tauran; Julien Verlaguet; Kartik Khandelwal; Khyathi Raghavi Chandu; Kilian Tep; Konstantin Mishchenko; Kris Szczepaniak; Kush Jain; Larissa Laich; Laura Calem; Laurence Aitchison; Laurent Callot; Laurent Fainsin; Léo Cotteleer; Léonard Blier; Loïc Chadoutaud; Loïck Chambon; Lorenzo Proietti; Louis Faucon; Louis Martin; Louis Serrano; Lu Li; Luc Boudier; Lucas Fernandes Martins; Lucas Mebille; Lucile Saulnier; Ludovic Ho Fuh; Luis Montero; Łukasz Borchmann; Maarten Buyl; Malik Hassan Raza; Manon Chossegros; Marcin Możejko; Margaret Jennings; Markus Hennerbichler; Martin Alexandre; Mathieu Poirée; Mathieu Schmitt; Mathilde Guillaumin; Mathis Felardos; Matthieu André; Matthieu Dinot; Matthieu Futeral; Maurits Bleeker; Mauro Comi; Max Mynter; Maxim Berman; Maxime Darrin; Maxime Langelier; Maxime Louis; Maximilian Augustin; Maximilian Müller; Mehdi Bouaziz; Melina Jingting Laimon; Mert Unsal; Mia Chiquier; Michael Pilcer; Michał Pietruszka; Michał Zając; Mickaël Seznec; Mikhail Biriuchinskii; Minh-Quang Pham; Minwoo Kang; Mircea Lica; Morgane Rivière; Namit Katariya; Natasha Ørregaard Klingenbrunn; Nathan Bout; Nathan Grinsztajn; Nathan Simpson; Neeraj Aggarwal; Neil Ashton; Neil Mallinar; Nick Bührer; Nicolas Moreau; Nicolò Lucchesi; Ola Mysiak; Oliver Leicht; Olivier Bousquet; Olivier Koch; Parag Jain; Patricia Wang; Patrick Blies; Patrick von Platen; Patryk Saffer; Paul Jacob; Paul Teiletche; Paul Wambergue; Paula Kurylowicz; Pavan Kumar Reddy; Pavel Kuksa; Philippe Formont; Philippe Pinel; Philomène Chagniot; Pierre Glandon; Pierre Stock; Pierre-André Savalle; Piotr Miłoś; Poojan Shah; Prateek Gupta; Pravesh Agrawal; Pui Ki Chan; Quentin Desreumaux; Quentin Selle; Quentin Torroba; Quentin Wargnier; Quercus Hernandez; Ram Ramrakhya; Randall Isenhour; Ranjit Parva; Raphaël Balouka; Raphaël Rialland; Raul Perez Pelaez; Reinhard Sonnleitner; Remi Delacourt; Rishi Shah; Rob Romijnders; Rohan Shah; Rohin Arora; Romain Sauvestre; Roman Soletskyi; Ronan Riochet; Rosalie Millner; Rupert Menneer; Sagar Vaze; Samuel Barry; Samuel Belkadi; Samuel Humeau; Samuele Papa; Sanchit Gandhi; Sandeep Cranganore; Sandeep Subramanian; Sarthak Mittal; Saskia Adaime; Scott Matthews; Sean Cha; Sebastian Kaltenbach; Seungjae Jung; Shashwat Verma; Sherif Waly; Shrimai Prabhumoye; Siddhant Waghjale; Siddharth Gandhi; Simon Lepage; Simon Sorg; Soham Ghosh; Sophie Marbach; Srijan Mishra; Stanislas Lange; Steve Hong; Sumukh Aithal; Szymon Antoniak; Tarun Kumar Vangani; Teddy Turquet; Teven Le Scao; Théo Cachet; Thibaut LaLine truncated
|
||||
| 15 | 2610.37584 | REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation | Yuxi Huang; Silin Zhou; Chenhao Wang; Zihan Li; Gangming Guo; Pei Ke; Shen Gao; Shuo Shang | 2026-10-27 | 2026-10-27 | cs.IR; cs.AI | cs.IR | Personalized recommendation depends on learning se… |
|
||||
| 16 | 2610.37571 | TeamGym: A Gym for Team Decision-Making by AI Agents with Distributed Information | Chanwoo Park; Jaywoong Jeong; Zachary Wojtowicz; Yubin Kim; Taekyun Lee; Kaiqing Zhang; Asuman Ozdaglar | 2026-10-27 | 2026-10-27 | cs.AI | cs.AI | Many real-world decisions require teams to integra… |
|
||||
| 17 | 2610.37567 | Gym-Anything-RT: Scaling Real-Time Environments for Vision-Language Agents | Pranjal Aggarwal; Sean Welleck | 2026-10-27 | 2026-10-27 | cs.LG; cs.AI | cs.LG | AI agents have made substantial progress in domain… |
|
||||
| 18 | 2610.37561 | When uncertainty quantification fails: structural vulnerabilities and corrections for selective prediction under clinical class imbalance | Walter Endrizzi; Flavio Ragni; Raffaele Marchesi; Stefano Bovo; Monica Moroni; Giuseppe Jurman; Venet Osmani | 2026-10-27 | 2026-10-27 | cs.LG; cs.AI | cs.LG | Background. Selective prediction systems improve t… |
|
||||
| 19 | 2610.37550 | Kinematic Constraint-Referenced Evaluation for Articulated Object Manipulation | Baptiste Bonin; Caro Strickland; Audrey Durand | 2026-10-27 | 2026-10-27 | cs.RO; cs.AI | cs.RO | Manipulation policies are evaluated predominantly … |
|
||||
| 20 | 2610.37547 | When, Where, and What to Correct: Human-Guided Adaptive Residual Correction for Robot Policies | Anukriti Singh; Maxime Caniot; Pratap Tokekar; Firas Abi-Farraj | 2026-10-27 | 2026-10-27 | cs.RO; cs.AI | cs.RO | Imitation policies that reliably execute most of a… |
|
||||
@@ -0,0 +1,21 @@
|
||||
rank arxiv_id title authors published updated categories primary_category abstract
|
||||
1 2610.37668 Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction Prakhar Kaushik; Soumava Paul; Alan Yuille 2026-10-27 2026-10-27 cs.CV; cs.AI; cs.GR; cs.LG cs.CV Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resource-constrained settings. We introduce Hexels: novel planar hexagonal surface elements with a first-order spatial color field for ef
|
||||
2 2610.37666 ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning Chaehyun Kim; Chi-Pin Huang; Jisoo Kim; Min-Hung Chen; Yu-Chiang Frank Wang; Seungryong Kim; Fu-En Yang 2026-10-27 2026-10-27 cs.RO; cs.AI; cs.CV cs.RO Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the diversity and coverage of action-labeled robot demonstrations. Human videos provide much broader behavioral and environmental experience, while learning fro
|
||||
3 2610.37656 Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops Aakash Sarkar; Ananya Mukherjee; Motoshige Sato 2026-10-27 2026-10-27 cs.LG; cs.AI; physics.comp-ph cs.LG Relations compose through the entity they share - Alice is Bob's mother and Bob is Carol's father, so Alice is Carol's grandmother - and the order matters, since a father's mother is not a mother's father; verifying a composed relation means closing the loop. We show that if each entity's coordinate
|
||||
4 2610.37655 KPPax: preprocess differentiable kinetic ODE for machine learning in atmospheric chemistry Wenqing Peng; Michael Boy; Zhi-Song Liu 2026-10-27 2026-10-27 cs.AI cs.AI Atmospheric chemical mechanisms are commonly distributed in the language of the Kinetic PreProcessor (KPP), which generates efficient Fortran or C code but does not fit into the differentiable programming frameworks in which machine-learning models are developed. We present KPPax, a kinetic preproce
|
||||
5 2610.37649 Can LLMs Uncover Hidden Physical Laws through Free Exploration? Zhen Yang; Wen Wang; Xander Xu; Ying-Cong Chen 2026-10-27 2026-10-27 cs.CL; cs.AI; cs.MA cs.CL Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notice unexpected behavior, such as heavier objects falling more slowly, and discover the law through experiments without bei
|
||||
6 2610.37647 MuonGS: Pretraining LLMs with Relaxed Weight-Norm Control Athanasios Glentis; Dawei Li; Mingyi Hong 2026-10-27 2026-10-27 cs.LG; cs.AI; math.OC cs.LG Weight decay and explicit weight-norm constraints improve optimizer performance in language model pretraining, yet a unified understanding of why such control helps and how much is needed remains incomplete. We analyze norm control in Muon over the entire training trajectory using the \emph{accumula
|
||||
7 2610.37631 What Improves During Pretraining? Tracking Knowledge Acquisition with Point-in-Time Models Chang Su; Bin Wu; Emine Yilmaz; Yao Lu 2026-10-27 2026-10-27 cs.AI cs.AI Language models pretrained on web corpora collected over multiple years learn both general and domain-specific knowledge. How these different kinds of knowledge are learned as pretraining progresses remains unclear. Recent point-in-time models trained on web snapshots from different years provide a
|
||||
8 2610.37624 Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions Anouar Imel; Imad Charradi; Abderrahman Sghir; Khalil El Khammar 2026-10-27 2026-10-27 cs.AI; cs.CL; cs.MA; cs.SI cs.AI When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claims relevant to the decision criteria. On hidden-profile tasks both look attractive, because how widely a fact is held is
|
||||
9 2610.37613 VideoLVR: Latent Visual Reasoning over Grounded Video Evidence Shilong Li; Xingyuan Bu; Hao Shi; Yun Xing; Weixin Feng; Qiangpeng Yang; Shilei Wen 2026-10-27 2026-10-27 cs.CV; cs.AI cs.CV Chain-of-thought reasoning has substantially advanced video understanding in multimodal large language models (MLLMs). However, language-based reasoning traces do not provide a reliable mechanism for models to revisit relevant visual evidence, leading to visual forgetting and impairing their ability
|
||||
10 2610.37605 Beyond Answer Changes: Matched Same-Class Controls for Local Audio Evidence Yunuo Wang; Maoyuan Chen; Yuanjin Huang; Xing Liu 2026-10-27 2026-10-27 cs.SD; cs.AI cs.SD For audio-language models, an answer change after a local sound-event edit can reflect a response to the event's class, sensitivity to waveform rewriting, or both. We compare matched same-class and different-class replacements of a queried event. Both use the same interval, level estimate, donor fit
|
||||
11 2610.37599 MoI-Bench: A Benchmark for Image Generation and Editing on Mobile Devices Kailai Feng; Haoxiang Rao; Yuxiang Wei; Bo Chen; Junsong Li; Yang Pan; Chengkun Cai; Jagmohan Chauhan 2026-10-27 2026-10-27 cs.CV; cs.AI cs.CV Developing on-device image models requires considering practical user needs, task types and device resource constraints. However, existing benchmarks provide limited guidance on identifying capability gaps between on-device models and server-side models. We introduce MoI-Bench, a benchmark grounded
|
||||
12 2610.37598 GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting Joseph Natter; Long Vu; Yifan Zhang; Bobin Deng; Kun Suo; Rui Wu 2026-10-27 2026-10-27 cs.LG; cs.AI; cs.NE cs.LG Traffic forecasting requires modeling complex temporal dynamics and the spatial dependencies imposed by road topology. Supervised graph-based models achieve strong performance, but are often trained for a particular dataset and sensor graph, making deployment to new or evolving networks costly. Prio
|
||||
13 2610.37588 Understanding the limits of latent world models Rodrigo Gonzalez Laiz; Steffen Schneider 2026-10-27 2026-10-27 cs.LG; cs.AI cs.LG World models are widely proposed as core components for enabling agents to reason over long temporal and spatial horizons. Yet current evaluations often emphasize task performance while providing limited insight into whether learned world models acquire predictive latent dynamics that reflect the un
|
||||
14 2610.37585 Timestral Adrien Petralia; Alexandre Gavaudan; Artjom Joosen; Etienne Goffinet; Richard Kurle; Yassine El Ouahidi; Yassir Bendou; Abdelaziz Bounhar; Abhijeet Somani; Aditi Kabra; Adrian Valente; Adrien Sadé; Ahmed Djermani; Alan Jeffares; Albert Jiang; Alberto Bietti; Aleksandr Timashov; Alexandre Cahill; Alexandre Laval; Alexandre Sablayrolles; Alexandros Sanchez Vassopoulos; Amélie Héliou; Amos You; André Jonasson; Andreas Fürst; Andrew Bai; Andrew Ehrenberg; Andrew Zhao; Andy Lo; Angele Lenglemetz; Anmol Agarwal; Antonia Calvi; Arata Suzuki; Arjun Majumdar; Arthur Fournier; Ashwani Kumar; Augustin Lombard; Avinash Sooriyarachchi; Aylin Guliz Akkus; Aysenur Karaduman; Baptiste Bout; Baptiste Rozière; Barna Pásztor; Baudouin De Monicault; Benjamin Holzschuh; Benjamin Tibi; Benno Stein; Bernhard Stadlbauer; Bhargavi Bhaskar; Binbing Hou; Błażej Osiński; Boris van Breugel; Camille Le Scao; Chaoran Yu; Charlotte Cronjäger; Chen-Yo Sun; Chris Bamford; Christian Wallenwein; Christophe Renaudin; Clémence Lanfranchi; Colin Bonatti; Corentin Barreau; Corentin Sautier; Cristiana-Diana Diaconu; Cyprien Courtot; Daniel Lopes; Daniel Marczak; Darius Dabert; Diego de las Casas; Dominik Nuss; Dylan Rubini; Dzmitry Soupel; Elizaveta Demyanenko; Elliot Chane-Sane; Emilien Fugier; Emmanuel Gottlob; Erik Aas; Etienne Duchesne; Fabian Paischer; Fabian Schlager; Faruk Ahmed; Federico Baldassarre; Félix Rosseeuw; Filip Szatkowski; Filippo Vicentini; Florian Wiesner; Gabrielle Berrada; Gaëtan Ecrepont; Gaspard Blanchet; Gaspard Donada-Vidal; Gaurav Mahajan; Gauthier Guinet; Genevieve Hayes; Georgii Novikov; Georgios Christoglou; Giada Pistilli; Gonzague de Carpentier; Graeme Nail; Guillaume Breton; Guillaume Kunsch; Guillaume Lample; Guillaume Martin; Guillaume Raille; Guillaume Richard; Guillem Simeon; Gunjan Dhanuka; Gunshi Gupta; Hamza Senhaji Rhazi; Han Zhou; Hédi Hadiji; Himanshu Jaju; Hope McGovern; Hubert de Parseval; Hugo Cisneros; Hugo Germain; Hugo Thimonier; Hugo Venturini; Hyeonju Lee; Hyunwoo Oh; Iliass Lasri; Ilyas Oulkadda; Jacques Sun; Jan Ludziejewski; Jason Rute; Jean de Becdelièvre; Jean Quentin; Jean-Malo Delignon; Jessica Chudnovsky; Jianchao Li; Jie Zhang; Jin Bin Ou; Joachim Studnia; Joep Barmentlo; Johannes Brandstetter; John Harvill; Jonas Amar; Jonas Schweizer; Jonathan Roberts; Joséphine Delas; Josselin Somerville; Jules Depersin; Julien Denize; Julien Tauran; Julien Verlaguet; Kartik Khandelwal; Khyathi Raghavi Chandu; Kilian Tep; Konstantin Mishchenko; Kris Szczepaniak; Kush Jain; Larissa Laich; Laura Calem; Laurence Aitchison; Laurent Callot; Laurent Fainsin; Léo Cotteleer; Léonard Blier; Loïc Chadoutaud; Loïck Chambon; Lorenzo Proietti; Louis Faucon; Louis Martin; Louis Serrano; Lu Li; Luc Boudier; Lucas Fernandes Martins; Lucas Mebille; Lucile Saulnier; Ludovic Ho Fuh; Luis Montero; Łukasz Borchmann; Maarten Buyl; Malik Hassan Raza; Manon Chossegros; Marcin Możejko; Margaret Jennings; Markus Hennerbichler; Martin Alexandre; Mathieu Poirée; Mathieu Schmitt; Mathilde Guillaumin; Mathis Felardos; Matthieu André; Matthieu Dinot; Matthieu Futeral; Maurits Bleeker; Mauro Comi; Max Mynter; Maxim Berman; Maxime Darrin; Maxime Langelier; Maxime Louis; Maximilian Augustin; Maximilian Müller; Mehdi Bouaziz; Melina Jingting Laimon; Mert Unsal; Mia Chiquier; Michael Pilcer; Michał Pietruszka; Michał Zając; Mickaël Seznec; Mikhail Biriuchinskii; Minh-Quang Pham; Minwoo Kang; Mircea Lica; Morgane Rivière; Namit Katariya; Natasha Ørregaard Klingenbrunn; Nathan Bout; Nathan Grinsztajn; Nathan Simpson; Neeraj Aggarwal; Neil Ashton; Neil Mallinar; Nick Bührer; Nicolas Moreau; Nicolò Lucchesi; Ola Mysiak; Oliver Leicht; Olivier Bousquet; Olivier Koch; Parag Jain; Patricia Wang; Patrick Blies; Patrick von Platen; Patryk Saffer; Paul Jacob; Paul Teiletche; Paul Wambergue; Paula Kurylowicz; Pavan Kumar Reddy; Pavel Kuksa; Philippe Formont; Philippe Pinel; Philomène Chagniot; Pierre Glandon; Pierre Stock; Pierre-André Savalle; Piotr Miłoś; Poojan Shah; Prateek Gupta; Pravesh Agrawal; Pui Ki Chan; Quentin Desreumaux; Quentin Selle; Quentin Torroba; Quentin Wargnier; Quercus Hernandez; Ram Ramrakhya; Randall Isenhour; Ranjit Parva; Raphaël Balouka; Raphaël Rialland; Raul Perez Pelaez; Reinhard Sonnleitner; Remi Delacourt; Rishi Shah; Rob Romijnders; Rohan Shah; Rohin Arora; Romain Sauvestre; Roman Soletskyi; Ronan Riochet; Rosalie Millner; Rupert Menneer; Sagar Vaze; Samuel Barry; Samuel Belkadi; Samuel Humeau; Samuele Papa; Sanchit Gandhi; Sandeep Cranganore; Sandeep Subramanian; Sarthak Mittal; Saskia Adaime; Scott Matthews; Sean Cha; Sebastian Kaltenbach; Seungjae Jung; Shashwat Verma; Sherif Waly; Shrimai Prabhumoye; Siddhant Waghjale; Siddharth Gandhi; Simon Lepage; Simon Sorg; Soham Ghosh; Sophie Marbach; Srijan Mishra; Stanislas Lange; Steve Hong; Sumukh Aithal; Szymon Antoniak; Tarun Kumar Vangani; Teddy Turquet; Teven Le Scao; Théo Cachet; Thibaut Lavril; ThLine truncated
|
||||
15 2610.37584 REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation Yuxi Huang; Silin Zhou; Chenhao Wang; Zihan Li; Gangming Guo; Pei Ke; Shen Gao; Shuo Shang 2026-10-27 2026-10-27 cs.IR; cs.AI cs.IR Personalized recommendation depends on learning semantic and collaborative relations among items from online content and user interactions. Generative recommendation (GR) offers a promising paradigm by autoregressively generating discrete semantic IDs (SIDs) of items. However, randomly initialized S
|
||||
16 2610.37571 TeamGym: A Gym for Team Decision-Making by AI Agents with Distributed Information Chanwoo Park; Jaywoong Jeong; Zachary Wojtowicz; Yubin Kim; Taekyun Lee; Kaiqing Zhang; Asuman Ozdaglar 2026-10-27 2026-10-27 cs.AI cs.AI Many real-world decisions require teams to integrate information distributed across participants. Yet AI agents are still primarily trained and benchmarked in isolation. We introduce TeamGym, an environment for evaluating and training language model-based agents on team decision-making problems cons
|
||||
17 2610.37567 Gym-Anything-RT: Scaling Real-Time Environments for Vision-Language Agents Pranjal Aggarwal; Sean Welleck 2026-10-27 2026-10-27 cs.LG; cs.AI cs.LG AI agents have made substantial progress in domains where they have a non-trivial amount of time to deliberate between actions, such as mathematics, software engineering, and performing tasks on desktop applications. It is less clear how such models fare in settings that demand real-time interaction
|
||||
18 2610.37561 When uncertainty quantification fails: structural vulnerabilities and corrections for selective prediction under clinical class imbalance Walter Endrizzi; Flavio Ragni; Raffaele Marchesi; Stefano Bovo; Monica Moroni; Giuseppe Jurman; Venet Osmani 2026-10-27 2026-10-27 cs.LG; cs.AI cs.LG Background. Selective prediction systems improve the safety of clinical artificial intelligence by deferring ambiguous cases to human experts while automating high-confidence decisions. However, this safety mechanism relies entirely on the premise that uncertainty scores accurately reflect clinical
|
||||
19 2610.37550 Kinematic Constraint-Referenced Evaluation for Articulated Object Manipulation Baptiste Bonin; Caro Strickland; Audrey Durand 2026-10-27 2026-10-27 cs.RO; cs.AI cs.RO Manipulation policies are evaluated predominantly by binary task success, which cannot tell whether the commanded gesture is the one the object's kinematics admit. We introduce Constraint-Referenced Strategy (CRS), which projects the commanded end-effector twist onto the object's joint axis, separat
|
||||
20 2610.37547 When, Where, and What to Correct: Human-Guided Adaptive Residual Correction for Robot Policies Anukriti Singh; Maxime Caniot; Pratap Tokekar; Firas Abi-Farraj 2026-10-27 2026-10-27 cs.RO; cs.AI cs.RO Imitation policies that reliably execute most of a manipulation trajectory can still fail in localized regions requiring last-mile precision. Updating the full policy or exploring residual actions everywhere treats this local failure as a global learning problem. We introduce Adaptive Residual Corre
|
||||
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,153 @@
|
||||
#!/usr/bin/env python3
|
||||
"""arXiv cs.AI recent-papers extraction + re-verification gate.
|
||||
|
||||
Extract latest arXiv cs.AI submissions from the pinned raw API response
|
||||
(raw_api.xml) into TSV / JSON / Markdown tables, then re-derive from the same
|
||||
XML and diff against the committed tables. Exit 0 only on an exact match.
|
||||
|
||||
Usage:
|
||||
python3 reverify.py emit # write tsv / json / md from raw_api.xml
|
||||
python3 reverify.py verify # re-derive and diff against committed files
|
||||
"""
|
||||
import csv
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
import xml.etree.ElementTree as ET
|
||||
|
||||
HERE = "/root/troupe-standup/wizard-work/ledger/2026-10-28-arxiv-csai-recent"
|
||||
NS_ATOM = "http://www.w3.org/2005/Atom"
|
||||
|
||||
ABSTRACT_LIMIT = 300
|
||||
TITLE_LIMIT = 90
|
||||
ABSTRACT_SHOW = 50
|
||||
|
||||
FIELDS = ["rank", "arxiv_id", "title", "authors", "published", "updated",
|
||||
"categories", "primary_category", "abstract"]
|
||||
|
||||
|
||||
def text(el, tag):
|
||||
child = el.find(f"{{{NS_ATOM}}}{tag}")
|
||||
return child.text.strip() if child is not None and child.text else ""
|
||||
|
||||
|
||||
def derive(root):
|
||||
"""Re-derive the row list from the raw Atom feed. Pure function of XML."""
|
||||
rows = []
|
||||
for e in root.findall(f"{{{NS_ATOM}}}entry"):
|
||||
rid = text(e, "id")
|
||||
m = re.search(r"arxiv\.org/abs/(\d+\.\d+)(?:v\d+)?", rid)
|
||||
arxiv_id = m.group(1) if m else rid
|
||||
title = text(e, "title")
|
||||
published = text(e, "published")[:10]
|
||||
updated = text(e, "updated")[:10]
|
||||
authors = [text(a, "name") for a in e.findall(f"{{{NS_ATOM}}}author")]
|
||||
cats = [c.get("term") for c in e.findall(f"{{{NS_ATOM}}}category")]
|
||||
abstract = text(e, "summary")
|
||||
rows.append({
|
||||
"arxiv_id": arxiv_id,
|
||||
"title": title,
|
||||
"authors": "; ".join(authors),
|
||||
"published": published,
|
||||
"updated": updated,
|
||||
"categories": "; ".join(cats),
|
||||
"primary_category": cats[0] if cats else "",
|
||||
"abstract": abstract[:ABSTRACT_LIMIT],
|
||||
})
|
||||
# arXiv API returns descending by submitted date.
|
||||
rows.sort(key=lambda r: r["published"], reverse=True)
|
||||
for i, r in enumerate(rows, 1):
|
||||
r["rank"] = i
|
||||
return rows
|
||||
|
||||
|
||||
def fmt_tsv(rows):
|
||||
out = io.StringIO()
|
||||
w = csv.DictWriter(out, fieldnames=FIELDS, delimiter="\t", lineterminator="\n")
|
||||
w.writeheader()
|
||||
w.writerows(rows)
|
||||
return out.getvalue()
|
||||
|
||||
|
||||
def fmt_json(rows):
|
||||
return json.dumps(rows, indent=2, ensure_ascii=False) + "\n"
|
||||
|
||||
|
||||
def fmt_md(rows):
|
||||
lines = [
|
||||
"# arXiv cs.AI — most recent 20 submissions (fetched 2026-10-28)",
|
||||
"",
|
||||
"Source: `raw_api.xml` (API: cat:cs.AI, sortBy=submittedDate, sortOrder=descending, max_results=20)",
|
||||
"",
|
||||
"| Rank | arXiv | Title | Authors | Published | Updated | Categories | Primary | Abstract (first 50 chars) |",
|
||||
"|---:|---|---|---|---|---|---|---|---|",
|
||||
]
|
||||
for r in rows:
|
||||
title = r["title"].replace("|", "\\|")
|
||||
abstract = r["abstract"][:ABSTRACT_SHOW] + ("…" if len(r["abstract"]) > ABSTRACT_SHOW else "")
|
||||
lines.append(f"| {r['rank']} | {r['arxiv_id']} | {title} | {r['authors']} | "
|
||||
f"{r['published']} | {r['updated']} | {r['categories']} | {r['primary_category']} | {abstract} |")
|
||||
return "\n".join(lines) + "\n"
|
||||
|
||||
|
||||
def emit(rows, out_dir):
|
||||
tsv = out_dir + "/arxiv_csai_recent.tsv"
|
||||
js = out_dir + "/arxiv_csai_recent.json"
|
||||
md = out_dir + "/arxiv_csai_recent.md"
|
||||
with open(tsv, "w", encoding="utf-8", newline="") as f:
|
||||
f.write(fmt_tsv(rows))
|
||||
with open(js, "w", encoding="utf-8") as f:
|
||||
f.write(fmt_json(rows))
|
||||
with open(md, "w", encoding="utf-8") as f:
|
||||
f.write(fmt_md(rows))
|
||||
return tsv, js, md
|
||||
|
||||
|
||||
def verify(out_dir):
|
||||
root = ET.parse(out_dir + "/raw_api.xml").getroot()
|
||||
expected = derive(root)
|
||||
expected_tsv = fmt_tsv(expected)
|
||||
expected_json = fmt_json(expected)
|
||||
expected_md = fmt_md(expected)
|
||||
files = {
|
||||
"tsv": out_dir + "/arxiv_csai_recent.tsv",
|
||||
"json": out_dir + "/arxiv_csai_recent.json",
|
||||
"md": out_dir + "/arxiv_csai_recent.md",
|
||||
}
|
||||
ok = True
|
||||
for name, path in files.items():
|
||||
with open(path, encoding="utf-8") as f:
|
||||
actual = f.read()
|
||||
if name == "tsv":
|
||||
want = expected_tsv
|
||||
elif name == "json":
|
||||
want = expected_json
|
||||
else:
|
||||
want = expected_md
|
||||
if actual != want:
|
||||
ok = False
|
||||
print(f"FAIL {name}: committed content differs from re-derivation")
|
||||
if name in ("tsv", "json", "md"):
|
||||
# Show first differing line for diagnosis.
|
||||
a_lines = actual.splitlines()
|
||||
w_lines = want.splitlines()
|
||||
for i in range(max(len(a_lines), len(w_lines))):
|
||||
a = a_lines[i] if i < len(a_lines) else "<missing>"
|
||||
w = w_lines[i] if i < len(w_lines) else "<missing>"
|
||||
if a != w:
|
||||
print(f" first diff at line {i+1}:\n actual: {a[:100]}\n expected: {w[:100]}")
|
||||
break
|
||||
if ok:
|
||||
print(f"PASS re-derived from raw_api.xml; table has {len(expected)} rows")
|
||||
return 0 if ok else 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import io
|
||||
mode = sys.argv[1] if len(sys.argv) > 1 else "emit"
|
||||
if mode == "emit":
|
||||
rows = derive(ET.parse(HERE + "/raw_api.xml").getroot())
|
||||
for f in emit(rows, HERE):
|
||||
print(f"WROTE {f}")
|
||||
else:
|
||||
sys.exit(verify(HERE))
|
||||
Reference in new issue
Block a user