|
|
|
@@ -0,0 +1,152 @@
|
|
|
|
|
[
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32978v1",
|
|
|
|
|
"title": "SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning",
|
|
|
|
|
"authors": "Yuhan Liu, Lianhui Qin, Shenji Wan",
|
|
|
|
|
"published": "2026-10-23T17:59:21Z",
|
|
|
|
|
"updated": "2026-10-23T17:59:21Z",
|
|
|
|
|
"category": "cs.CV",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. Language-guided methods support semantic planning and object-level reasoning, but precise spatial grounding remains difficult. Visual generative models offer rich priors over plausible arrangements, yet their outputs require geometric reasoning to become physically valid 3D scenes. We introduce SceneBloom, an agentic framework that combines visual layout sampling with contract-guided 3D compilation. A hierarchical sampler uses diffusion priors to generate furniture arrangements within functional zones. A compiler then uses relations extracted from each proposal to guide geometric fitting and local pose correction. Across five room types, SceneBloom attains the highest visual quality and physical stability among the compared methods and is the only method with no detected mesh collisions and out-of-bounds objects. Its layouts are also closer to the distribution of real rooms than those of all compared baselines. Object navigation policies trained in these realistic scenes achieve a higher success rate in held-out real scans than those trained on an equal number of real training scans. Code is available at https://github.com/Tinaliu0123/scenebloom."
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32971v1",
|
|
|
|
|
"title": "RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms",
|
|
|
|
|
"authors": "Xi Chen, Fengqi Hu, Zeyu Shen, Jiaying Xu, Shangding Gu, Pan Xu, Anqi Liu, Laixi Shi",
|
|
|
|
|
"published": "2026-10-23T17:57:22Z",
|
|
|
|
|
"updated": "2026-10-23T17:57:22Z",
|
|
|
|
|
"category": "cs.LG",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "Robust reinforcement learning (RL) is critical for reliable real-world deployment, where policies may fail under diverse shifts and disruptions. Existing robust RL algorithms offer a rich set of mechanisms and principles, yet two major barriers limit their broader potential: limited algorithm reusability and an unclear empirical capability boundary. We introduce RobustRLlib, an algorithm-centric library and benchmark that addresses both challenges. It integrates 17 representative robust online, offline, and safe RL algorithms under a unified interface for substantially improved reusability, together with an enhanced evaluation platform spanning diverse real-world shifts and advanced humanoid and vision-language-action tasks. Systematic evaluation over 273 perturbation configurations provides an up-to-date capability map of current robust RL algorithms, revealing where they remain effective and where substantial robustness gaps persist. As an open-source, user-friendly platform, RobustRLlib offers a reproducible and extensible codebase for applying existing methods to new problems and developing new robust RL algorithms."
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32969v1",
|
|
|
|
|
"title": "DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection",
|
|
|
|
|
"authors": "Amber Xie, Jiawei Fu, Xiaofeng Guo, Carmelo Sferrazza, Guanya Shi, Haozhi Qi",
|
|
|
|
|
"published": "2026-10-23T17:56:28Z",
|
|
|
|
|
"updated": "2026-10-23T17:56:28Z",
|
|
|
|
|
"category": "cs.RO",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "Collecting high-quality demonstrations remains a central bottleneck for learning dexterous manipulation. Teleoperation records executable robot actions, but it requires a complete robot setup and places the burden of coordinating many finger joints on the operator. Human demonstrations are easier to collect, but their motions must be estimated and retargeted to the robot, and they do not directly provide robot actions. In this paper, we introduce DexPort, a portable data-collection interface for high-DoF robot hands. It uses the same hand hardware for collection and deployment, avoiding a hand embodiment gap, and records both commanded joint targets and measured joint states. Our key observation is that a small set of skills can support a wide range of dexterous tasks. During collection, the operator moves the hand-held interface to specify the robot wrist motion and selects or adjusts skills that coordinate the finger motion. This removes the need to control each joint independently while retaining behaviors such as precise grasping and in-hand manipulation. We collect demonstrations across several real-world tasks and in unstructured environments without a robot arm. We then use behavior cloning to train visuomotor policies directly on the recorded wrist motions and hand commands, without skill labels. We evaluate across 4 tasks: pick-and-place with diverse objects, screwing with in-hand tool use, drawer stowage which requires simultaneous grasp and pulling, and a bimanual scanning task. We collect over 2,500 demonstrations with our portable device, in both laboratory and in-the-wild settings. Across our tasks, we see an improvement from 11% to 64% when using recorded robot commands instead of states, and an improvement from 36% to 78% for task success when using in-the-wild data."
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32948v1",
|
|
|
|
|
"title": "Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models",
|
|
|
|
|
"authors": "Dianye Huang, Jiamei Guo, Yue Zhou, Mingde Li, Yi Xiong, Wei Wang, Nassir Navab, Zhongliang Jiang",
|
|
|
|
|
"published": "2026-10-23T17:40:58Z",
|
|
|
|
|
"updated": "2026-10-23T17:40:58Z",
|
|
|
|
|
"category": "cs.CV",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "Objective: To develop a unified vision-language model for prompt-conditioned quantitative ultrasound measurement that addresses the mismatch between continuous measurement targets and discrete token-based numerical prediction. Methods: This article presents HAD-VLM, a hybrid autoregressive-diffusion framework that combines autoregressive text generation with continuous measurement prediction within a shared backbone. Visual prompt tuning adapts the vision encoder to ultrasound images. A diffusion process predicts a five-component representation comprising caliper endpoint coordinates and measurement length. A post-processing strategy combining the proposed coordinate-length consistency mechanism with ensemble prediction is introduced to refine measurement estimates. We evaluate four echocardiographic measurement tasks on EchoNet-LVH, with additional assessments of medical question answering and X-ray vertebral measurement. Results: HAD-VLM achieves mean absolute errors of 1.36, 2.77, 3.05, and 1.16 mm for IVSd, LVIDd, LVIDs, and LVPWd, respectively, reducing errors by 21.4-37.6\\% relative to the Vicuna-based autoregressive baseline. It also outperforms fine-tuned Qwen3-VL and direct MLP regression across all four tasks. Medical question answering performance is preserved on the evaluated dataset. For X-ray vertebral measurement, HAD-VLM reduces mean absolute error from 11.4 to 6.7 pixels. Conclusion: Integrating autoregressive language generation with diffusion-based continuous prediction improves quantitative medical image measurement while retaining prompt-conditioned task flexibility. Significance: HAD-VLM provides a unified approach to combining language interaction with anatomically grounded numerical prediction for quantitative medical image analysis."
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32945v1",
|
|
|
|
|
"title": "Monetizing Intelligence: Advertising and Subscription Design on LLM Platforms",
|
|
|
|
|
"authors": "Yuhang Ji, Fasheng Xu, Tianjun Feng",
|
|
|
|
|
"published": "2026-10-23T17:39:42Z",
|
|
|
|
|
"updated": "2026-10-23T17:39:42Z",
|
|
|
|
|
"category": "econ.TH",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "Large language model (LLM) platforms introducing advertising must decide how much capability ad revenue should fund and what consumers should pay to avoid ads. We study a monopolistic platform that jointly chooses costly response quality, advertising intensity, and subscription prices when advertising reduces user value but better service raises advertising returns. Three findings follow. First, when partly ad-supported and ad-free plans coexist, advertising can finance useful service for consumers who receive none under pure subscription. Lower effective quality in middle plans weakens the alternatives available to premium users, allowing higher prices for unchanged ad-free service. Some fully ad-supported users gain utility, while partly ad-supported and ad-free users lose: broader access can coexist with utility polarization. Second, an intermediate advertising cap can maximize consumer surplus by preserving some revenue that finances service while limiting degradation. Third, cheaper compute can raise quality and reduce ad intensity, yet sufficiently large cost reductions can increase aggregate advertising revenue above its initial level because better service raises the value of the remaining advertised interactions. An extension shows how advertising-funded upgrades can bring plans to the same maximum capability and advertising exposure, eliminating the basis for different prices. These results make menu design central to evaluating LLM advertising: the consequences extend beyond users who see ads to the alternatives and prices faced by those who do not."
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32933v1",
|
|
|
|
|
"title": "Yalda-Embedding: Open Development of a Competitive Persian Retrieval Model",
|
|
|
|
|
"authors": "Yalda Taheri, Mohammad Hassan Heydari, Armon Rasooli",
|
|
|
|
|
"published": "2026-10-23T17:30:40Z",
|
|
|
|
|
"updated": "2026-10-23T17:30:40Z",
|
|
|
|
|
"category": "cs.CL",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "Despite advances in multilingual text representations, effective dense retrieval for Persian remains constrained by the limited availability of language-specific training resources and compact embedding models. We present Yalda Embedding, a 595.8-million-parameter Persian retrieval model adapted from Qwen3-Embedding-0.6B using more than one million query-document pairs. On eight Persian retrieval tasks from FaMTEB, the model achieves the highest macro-average among the evaluated 0.6B models, scoring 0.5488 and outperforming Qwen3-Embedding-0.6B and F2LLM-v2-0.6B on every task. It also approaches Qwen3-Embedding-4B, winning on four tasks, tying on one, and trailing by 0.0075 in macro-average. An incremental ablation study examines contrastive batch size, optimization stabilization, and relational knowledge distillation from F2LLM-v2-8B. Under the one-epoch training setup, contrastive fine-tuning alone yields a modest mean improvement over initialization and regressions on two tasks. The final distilled configuration improves all eight tasks over the non-distilled model, raising the mean from 0.4813 to 0.5488 without increasing inference-time model size. These gains include hard-negative evaluation tasks despite training without explicitly mined or supplied hard negatives. We release model weights, training and evaluation code, the pairwise dataset, and its teacher-embedded counterpart, enabling inspection of data composition and training procedures, independent evaluation, and reuse without repeating expensive teacher inference."
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32919v1",
|
|
|
|
|
"title": "SemantEq: Faithful Bidirectional Equivalence of Formal Statements",
|
|
|
|
|
"authors": "Xinrui Li, Pawan Sasanka Ammanamanchi, Siddharth Bhat, Rianna Jamdar, Yongxi Lin, Stella Biderman",
|
|
|
|
|
"published": "2026-10-23T17:20:12Z",
|
|
|
|
|
"updated": "2026-10-23T17:20:12Z",
|
|
|
|
|
"category": "cs.AI",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "Statement autoformalization translates mathematics from natural language into a proof assistant such as Lean 4, and models now do it at scale. As provers get stronger, the burden of correctness shifts from the proof to the statement, that is, to whether the formal statement faithfully translates its source. Given a trusted reference formalization, the natural test is logical equivalence, and it proves too much. $P \\leftrightarrow Q$ holds trivially for any two statements $P$ and $Q$ that the library proves, because a prover can prove each separately and pass through $P \\leftrightarrow \\mathrm{True} \\leftrightarrow Q$. The stronger the prover, the more unrelated pairs pass. Earlier methods restrict the prover and check that each proof names the other statement. We introduce SemantEq, a more principled relation that instead requires each statement to turn into the other only through a chain of allowed steps, such as logical rearrangement and rewriting with the library's own equations. Our programs judge a proof by the proof term Lean checks, not by its tactic script. SemantEq-Eval, a search without a model, reaches 100% precision and 65.6% recall on the ProofNetVerif test split under our adjudicated labels, against 95.8% and 61.8% for BEq+, and an 8.9-fold increase in its CPU time adds at most three pairs. A language model finds more proofs, but under two of four prompts it proves both directions of about two in five of the non-equivalent pairs. SemantEq-ProofAudit audits each model-written proof under a policy derived from the relation and accepts none of the 104 non-equivalent pairs, and it raises recall on 407 equivalent pairs from 65.4% to 81.1% under the best prompt. Separating the generation of equivalence proofs from their acceptance lets a stronger prover raise recall without changing what an acceptance means. We release code and data at: https://github.com/hlxr89/SemantEq"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32891v1",
|
|
|
|
|
"title": "Green Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code Optimizations",
|
|
|
|
|
"authors": "Sadra Emami, Benjamin Weigell, Mohammad Reza Mousavi, Gunel Jahangirova, Hugo Araujo, Bernhard Bauer",
|
|
|
|
|
"published": "2026-10-23T16:58:01Z",
|
|
|
|
|
"updated": "2026-10-23T16:58:01Z",
|
|
|
|
|
"category": "cs.SE",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "Large Language Models (LLMs) are increasingly used to optimize code for performance. This practice often assumes that improvements in execution speed naturally translate into overall lower energy consumption. We challenge this assumption empirically by measuring whether performance-optimized code produced by LLM self-refinement pipelines is also energy-efficient relative to canonical human reference solutions, and whether the energy cost of the optimization process can be offset by subsequent execution-time savings. We evaluate 11 open-source models across four decoding configurations on all 1,000 problems of EffiBench, a state-of-the-art performance benchmark, while collecting per-process, hardware-level energy measurements throughout. Inference energy spans 0.79 to 8.68 MJ across model-variant pairs, which is roughly equivalent to the energy of 250 to 2800 GPT-4.1 queries. Limiting the maximum number of output tokens has the largest impact, reducing energy use by up to 69% compared to the default configuration. On the execution side, 42 of 44 configurations produce code that consumes more energy per problem than the canonical human reference, with overheads ranging from +4% to +886%. The two exceptions achieve only marginal gains, with break-even points on the order of 10^6 to 10^7 executions. Mixture-of-Experts architectures consume substantially less inference energy than equivalently-sized dense models without sacrificing correctness, making architectural choice a more consequential sustainability lever than decoding parameters. Performance optimization and energy efficiency are not always aligned goals: LLM self-refinement consistently produces faster-seeking but energy-heavier code relative to what a human engineer would write. All artifacts are available at https://doi.org/10.5281/zenodo.23598170."
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32890v1",
|
|
|
|
|
"title": "Closing the Modality Gap via Simplex-Constrained Representations",
|
|
|
|
|
"authors": "Shubham Gupta, Siva Reddy, Perouz Taslakian, Valentina Zantedeschi, Cem Subakan",
|
|
|
|
|
"published": "2026-10-23T16:57:48Z",
|
|
|
|
|
"updated": "2026-10-23T16:57:48Z",
|
|
|
|
|
"category": "cs.AI",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "While multimodal contrastive models like CLIP and CLAP successfully learn shared representations, their embeddings typically exhibit a persistent \\emph{modality gap}. We propose addressing this separation through a purely geometric approach: changing the embedding domain from the unit sphere, $S^{d-1}$, to the probability simplex, $Δ^{d-1}$. Although both manifolds share the same intrinsic dimension, the simplex acts as a structural prior; its nonnegative, unit-mass constraints serve as a cross-modal calibration that forces both modalities to ground themselves in the same coordinate system. By attaching lightweight softmax adapters and using Total Variation similarity, we reduce the centroid $\\ell_2$ gap by 97--99\\% across five multimodal retrieval benchmarks. This confirms that simplicial geometry induces genuine semantic alignment, matching or exceeding the retrieval performance of standard unconstrained models."
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32881v1",
|
|
|
|
|
"title": "NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding",
|
|
|
|
|
"authors": "Nilesh Prasad Pandey, Jangseon Park, Jason Kong, Onat Gungor, Tajana Rosing",
|
|
|
|
|
"published": "2026-10-23T16:47:29Z",
|
|
|
|
|
"updated": "2026-10-23T16:47:29Z",
|
|
|
|
|
"category": "cs.AI",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "Reinforcement learning (RL) post-training improves the reasoning capabilities of large language models, but its cost is dominated by autoregressive rollout generation, which can exceed 70% of training time. Existing speculative-decoding methods are poorly suited to this setting: model-based drafters consume scarce GPU memory and may become misaligned as the policy evolves, while existing model-free methods do not explicitly exploit repetition across training epochs. We observe that recent rollouts of the same prompt provide a high-quality, self-updating draft source. Based on this insight, we propose NgramRL, a per-prompt n-gram drafter constructed from bounded recent rollout history. NgramRL requires no auxiliary model, drafter training, or persistent GPU-resident drafter state, while target-model verification preserves the rollout distribution. To hide CPU cache lookup and scheduling, we further introduce an adaptive fan-out prefetcher that predicts likely verification outcomes (j, b), consisting of the accepted draft length j and target-emitted continuation token b. A causal budget allocator concentrates prefetches on high-probability outcomes, while uncovered outcomes fall back to sequential lookup without changing committed tokens. Across two model families and three reasoning and structured-generation workloads, NgramRL commits 3.60-7.77 tokens per target-model forward in the warm-cache regime, up to 1.99x more than SuffixDecoding and 7.0x more than prompt-lookup decoding. On Spider, the prefetcher covers 96.6% of Qwen3-8B outcomes at a candidate budget of 16 and improves measured rollout throughput by 1.38x over synchronous NgramRL, approaching its 1.40x overlap ceiling."
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32878v1",
|
|
|
|
|
"title": "Advancing SVD-based LLM Compression via Layer-Wise Error Model Search",
|
|
|
|
|
"authors": "Moritz Thoma, Maximilian Groezinger, Maximilian Forstenhäusler, Emad Aghajanzadeh, Manoj Rohit Vemparala, Christos Anagnostopoulos, Pierpaolo Mori, Nael Fasfous, Alexander Frickenstein, Daniel Mueller-Gritschneder, Ulf Schlichtmann",
|
|
|
|
|
"published": "2026-10-23T16:46:00Z",
|
|
|
|
|
"updated": "2026-10-23T16:46:00Z",
|
|
|
|
|
"category": "cs.AI",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "Low-rank SVD-based compression offers a powerful strategy to reduce the computational costs of LLMs. However, existing methods face two key limitations: (i) global rank allocation, where uncalibrated error proxies fail to capture complex error propagation, and (ii) decomposition quality, where Fisher-based estimators suffer from severe rank collapse. In this work, we address these limitations by introducing Layer-wise Error Modeling Search (LEMS) and KFAC-SVD. LEMS advances rank allocation by introducing a layer-wise error surrogate that integrates local and global layer importance alongside a propagation bias, enabling effective global rank allocation via an ILP formulation. KFAC-SVD improves decomposition quality by utilizing token-wise statistics, mitigating the rank deficiency observed in prior Fisher-based SVD approaches. Across Mistral, Qwen3, and Llama 3 model families, we show that LEMS consistently outperforms existing search strategies, delivering significant zero-shot accuracy gains of up to 4.8 p.p. that generalize to model sizes of 70B parameters, while KFAC-SVD achieves an average perplexity improvement of 15%. Project page and code: https://lems-svd.github.io"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32874v1",
|
|
|
|
|
"title": "Do \"True\" and \"False\" Add Up to One? Complement Consistency in LLM-Agent Opinion Simulations",
|
|
|
|
|
"authors": "Anouar Imel, Jin Qi",
|
|
|
|
|
"published": "2026-10-23T16:44:20Z",
|
|
|
|
|
"updated": "2026-10-23T16:44:20Z",
|
|
|
|
|
"category": "cs.AI",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "In LLM-agent opinion simulations, each agent reports the probability that a claim is true after seeing its own previous probability and the probabilities reported by its neighbors, and that number becomes its state in the next round. If the number describes the agent's position rather than the sentence it was shown, then rewriting the claim as its complement and replacing every probability p with 1 - p should return the complementary answer, so the two reports should sum to one. We test this with three small open models: Qwen3-4B, Llama-3.2-3B and Gemma-3-4B. On 2,304 agent states taken from a running network simulation, Qwen's paired reports sum to 1.18 on average, and on 48 real fact-checking claims from AVeriTeC they again exceed one. A controlled benchmark of 24 worlds, each with exactly two possible outcomes, shows the same failure in all three models. The discrepancy is two to ten times larger than the change produced by a same-meaning paraphrase, and it persists under repeated sampling and across peer group sizes and report strengths. When the reports are fed back into two populations that start from complementary states, the populations do not remain mirror images: their divergence is positive after five rounds for every model. Averaging each answer with the complement of its paired answer restores consistency by construction and lowers Brier loss averaged over the two wordings, but at the final round it beats the better of the two original wordings for only one of the three models. A schedule-by-targeting experiment on the same model gives a small, stable interaction because such sweeps keep the claim wording fixed. Consistency under rewording therefore needs its own test before simulated probabilities are read as beliefs"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32869v1",
|
|
|
|
|
"title": "From Deliberately Constructed Systemic Representations of the World of Activity to Dialogue: A Five-Level Communication Architecture for Strong Language-Based ASI",
|
|
|
|
|
"authors": "Maxim Osovsky",
|
|
|
|
|
"published": "2026-10-23T16:41:54Z",
|
|
|
|
|
"updated": "2026-10-23T16:41:54Z",
|
|
|
|
|
"category": "cs.AI",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "This paper proposes a five-level organization of message formation and understanding within thinking and activity in which ASI participates. Its central thesis is that a language model's context is fundamentally incapable of presenting the foundations of utterance formation for examination and verification. These foundations are established in advance by acquired schemas, systemic representations of the world of activity, and connections accepted as true within them. Neither context nor trained LLM weights, in themselves, attest to the presence of deliberately constructed systemic representations. The five levels distinguish systemic representations of the world of activity, a particular situation cut out from those representations, its narrative description, the full sense of a message, and text. A situation's schema-model is not identical to a story about it. A recipient reconstructs the full sense from an abbreviated text through jointly constructed and agreed-upon representations and joint activity. Reverse work proceeds from the full sense through an extended description and the situation's schema-model to the reconstruction of systemic foundations. The theoretical foundations draw on the systems methodology of G. P. Shchedrovitskiy, the structural differential of A. Korzybski, and the Meaning-Text theory of I. A. Mel'chuk. The contribution is a specific systemic-activity organization of content for examining and adjusting message foundations and controlling the consequences of their transformation. Further research concerns large graphical models of activity on reconstructible systemic foundations, distinct from text generation from context."
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32866v1",
|
|
|
|
|
"title": "Interpretable sparse fine-tuning with TopKLoRA enables faithful circuit discovery",
|
|
|
|
|
"authors": "Marek Masiak, Andrzej Szablewski, Nicola Cancedda, Constantin Venhoff",
|
|
|
|
|
"published": "2026-10-23T16:37:29Z",
|
|
|
|
|
"updated": "2026-10-23T16:37:29Z",
|
|
|
|
|
"category": "cs.LG",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "Fine-tuning on datasets of unknown origin can create a backdoor in the trained model when the data includes poisoned examples. Difficult to localise and remove, backdoors can persist through safety training. While parameter-efficient fine-tuning methods capture the full parameter changes introduced during training, they are not easily interpretable. We present the full method of TopKLoRA, extending the preliminary proposal of Masiak et al. (2025), an interpretable-by-design LoRA variant in which only the $k$ largest adapter latents are active at each token. Unlike SAEs, TopKLoRA is trained purely on downstream loss, where optimisation pressure incentivises learning functionally causal latents. We demonstrate this sparse LoRA adapter in a sleeper-agent backdoor case study where we create model organisms by fine-tuning gemma-2-2b, Qwen2.5-1.5B, and Qwen2.5-7B on a poisoned instruction-following dataset. For each organism, we identify and ablate a circuit that is both necessary and sufficient to implement the backdoor. Furthermore, our new fine-tuning method produces sparse circuits that are up to an order of magnitude smaller than a dense LoRA baseline, allowing surgical ablation of the malicious capability without sacrificing instruction-following performance. Finally, we propose a technique to construct model organisms with localised circuits using TopKLoRA latents and gradient-routing, which we use to validate the findings of our circuit search algorithm. We consider these findings as a step toward interpretable-by-design architectures that provide faithful units of analysis without compromising model performance. We share our code: https://github.com/interpretable-finetuning/TopKLoRA."
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"arxiv_id": "2610.32864v1",
|
|
|
|
|
"title": "PoKER: A Probability of Kill Estimation Rate Model for Air-to-Air Missiles Using Machine Learning on Stochastic Targets",
|
|
|
|
|
"authors": "Joao P. A. Dantas, Andre N. Costa, Diego Geraldo, Marcos R. O. A. Maximo, Takashi Yoneyama",
|
|
|
|
|
"published": "2026-10-23T16:34:57Z",
|
|
|
|
|
"updated": "2026-10-23T16:34:57Z",
|
|
|
|
|
"category": "cs.LG",
|
|
|
|
|
"comment": "",
|
|
|
|
|
"summary": "This work introduces PoKER, a novel probabilistic model engineered to optimize missile launch effectiveness in air-to-air scenarios, specifically within Beyond Visual Range (BVR) air combat. Unlike conventional Weapon Engagement Zone (WEZ) models that delineate zones based on static distances such as maximum, minimum, and no-escape ranges, PoKER applies machine learning to predict kill probabilities more accurately by integrating the stochastic behaviors of targets and missile miss distances. This model dynamically evaluates target behavior, greatly expanding the predictive capabilities of engagement analysis. By factoring in elements such as warhead lethality, target and shooter orientations, and the specific conditions of engagement, PoKER provides important insights into engagement dynamics and quantifies success probabilities. Consequently, it can potentially be an important tool for BVR air combat pilots, improving operational decision-making within this specialized combat domain."
|
|
|
|
|
}
|
|
|
|
|
]
|
ledger committed