跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+229新增论文
+172其中 AI 相关
+31已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-13 10:11 · 全站最近入库：2026-11-13 10:10各信源进度 →

统计口径与数据新鲜度

统计 2026-11-12 10:29 — 2026-11-13 10:29（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-13 10:11最近发现新增版本：2026-11-13 10:10库内论文最新更新时间：2026-11-11 13:12

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

21,904 已收录论文18,495 AI 相关6,106 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 18,495 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-13 10:09（北京时间）
新论文 · v1arXiv:2610.38744

AtomTree: A Hierarchical Framework for State-Aware Embodied Instruction Following with LLMs

Haotian Zhai, Tianming Sha, Junnan Li

原文摘要

Embodied instruction following in interactive environments requires agents to interpret natural language commands and complete long-horizon tasks. Existing planners either rely on large labeled trajectories, or use few-shot and zero-shot LLM prompting that produces a whole plan in a single serial reasoning process. These approaches depend on linguistic common sense, commit to a plan from the initial instruction, and only update after failures, which weakens robustness and state awareness. We present AtomTree, a hierarchical framework for state-aware task planning with LLMs. AtomTree incrementally builds a tree of subgoals and actions, where the LLM decides at each step, from the current symbolic state, whether to further decompose or to output a grounded low-level action. A lightweight memory module summarizes past outcomes for reuse in later decisions. When a low-level action stalls, AtomTree triggers hierarchical backtracking replanning to return to the parent node and regenerate the subtree plan from the latest state, preventing continued drift along an incorrect trajectory. In zero-shot evaluation on the ALFRED benchmark, AtomTree outperforms prior LLM-based planners. Project page: https://zhaihaotian.github.io/atomtree-website/.

cs.RO · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38739

Streaming Speech Recognition on a Microcontroller: a 65.7M-Parameter Transducer in 2 and 4 Bits on the ESP32-P4

Billal Boumedine

原文摘要

We run Kroko, a 65.7M-parameter streaming Zipformer2 transducer for English, on the ESP32-P4, a microcontroller with two 400 MHz RISC-V cores, a 128-bit SIMD extension (PIE) and 32 MB of PSRAM, but no neural accelerator. Without any training, the encoder's 290 matrices are stored with 2 or 4 bits per weight in Hadamard-rotated groups: the width of each matrix comes from its measured sensitivity, and each matrix is first corrected toward the original model's output, then rounded with GPTQ and a search over the group norms. The released 71 MB of int8 weights become a 26.65 MB file. Activations are int16 between the matrix products and int8 into them. A C engine with hand-written PIE kernels processes each 1.28 s chunk of audio in 0.90 s on both cores, beam search included, and its PC build computes the same bits as the chip, so accuracy is measured on whole test sets. LibriSpeech WER is 4.34% on test-clean and 10.26% on test-other, against 3.94% and 9.17% for the released model; on FLEURS and Common Voice the gap grows to 2.3 and 1.1 points. A GPU simulator shows that the integer arithmetic costs nothing and that the whole gap comes from the weights, and an ablation on all of test-clean shows that GPTQ does most of the work. We also report the port's speed history, from 51.3 s to 0.62 s of encoder time per chunk, each design step measured again in one build, an attempt to reach 16 MB that stopped at 19.63 MB, and what did not work. We did not measure energy. The inference engine, the firmware and the 2/4-bit weights are available at https://github.com/BoumedineBillal/esp32-pie-asr.

eess.AS · cs.AR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38737

RuleForge: Inferring and Instantiating Latent Visual Rules as Executable Programs

Weifeng Xu, Yaxiong Wang, Zhedong Zheng

原文摘要

Visual rule reasoning asks whether multimodal models can recover an abstract concept from a few examples. Existing studies either infer rules from visual examples but evaluate only classification or verbalization, or supervise executable generation with rules provided as input. Consequently, the relationship between visual rule understanding and reliable rule instantiation remains insufficiently explored. We present Bongard-Forge100k, a controlled benchmark, together with RuleForge, a backbone-agnostic framework that jointly learns visual rule understanding and rule-conditioned executable generation. The benchmark contains 108,797 problems: 86,000 for training, 19,297 for testing familiar rules, and 3,500 for testing held-out rule compositions. The framework progresses through rule-understanding training, joint understanding and scene-program supervision, and refinement via execution-grounded reinforcement learning with Understanding Replay. Executing generated programs under multiple random seeds provides verifiable feedback on executability, rule satisfaction, diversity, and robustness. With UniLIP as the primary backbone, RuleForge improves multiple-choice accuracy over the base model by 20.93 percentage points on familiar rules and 28.42 percentage points on held-out rule compositions, while increasing scene-level rule satisfaction on familiar rules from 2.91% to 70.99%. Additional experiments on InternVL3.5, Qwen3-VL, and Show-o2 demonstrate the effectiveness of the proposed training data and framework across diverse multimodal architectures.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38732

Adversarial Self-Distillation

Mohammad Sadegh Akhondzadeh, Soroush H. Zargarbashi, Aleksandar Bojchevski

原文摘要

Even though current safety-aligned language models are able to refuse harmful requests, their guard can still be bypassed by adversarial perturbations. As in other domains, adversarial training is considered a standard defense. However, due to the autoregressive nature of language generation, supervised finetuning on template refusals does not necessarily teach the model to refuse. Evidence of this is that the adversarially trained model still complies when the attacker injects a compliant prefill. We propose Adversarial Self-Distillation (ASD), which extends a model's own safe behavior to the space of adversarial perturbations. The teacher (the model itself given the clean prompt) can refuse the harmful request by default, or with the help of an additional instruction in its context. ASD distills this knowledge to the student (which is the same model under attack) at the prefixes that the student visits (due to on-policy sampling). These potentially include compliant openings. ASD achieves lower attack success than state-of-the-art defenses with little loss in multiple-choice accuracy, and it becomes able to recover a refusal even after a compliant opening.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2402.19411

PaECTER: Patent-level Representation Learning using Citation-informed Transformers

Mainak Ghosh, Michael E. Rose, Sebastian Erhardt, Erik Buunk, Dietmar Harhoff

原文摘要

PaECTER is an open-source document-level encoder specific for patents. We fine-tune BERT for Patents with examiner-added citation information to generate numerical representations for patent documents. PaECTER performs better in similarity tasks than current state-of-the-art models used in the patent domain. More specifically, our model outperforms the patent specific pre-trained language model (BERT for Patents) and general-purpose text embedding models (e.g., E5, GTE, and BGE) on our patent citation prediction test dataset on different rank evaluation metrics. PaECTER predicts at least one most similar patent at a rank of 1.32 on average when compared against 25 irrelevant patents. Numerical representations generated by PaECTER from patent text can be used for downstream tasks such as classification, tracing knowledge flows, or semantic similarity search. Semantic similarity search is especially relevant in the context of prior art search for both inventors and patent examiners.

cs.IR · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38731

Value Function-Guided MPPI for Hierarchical Planning and Control in Off-Road Autonomous Navigation

Anoushka Alavilli, Raymond Song, Guanya Shi, Jeff Schneider

原文摘要

Autonomous navigation in off-road terrain is commonly achieved using hierarchical control and planning architectures that rely on explicit cost maps and one-way information flow from a high-level planner to a low-level controller, decoupling planning from the true execution cost experienced during control. We propose a hierarchical planning and control framework in which information flows bidirectionally, allowing the low-level controller to guide trajectory selection at the planning level. The highest level of the hierarchy is a Model Predictive Path Integral (MPPI) control-style planner that determines optimal trajectories and passes these waypoints to a pretrained low-level reinforcement learning (RL) controller. Rather than drawing from an explicit cost map, our MPPI planner leverages the value function of the RL controller as an implicit cost representation. In this formulation, MPPI serves as a trajectory exploration mechanism, while the low-level controller's value function guides the search. To account for the distribution shift seen by the value function between training and evaluation, we propose an online policy evaluation process that adapts the value function to unseen driving experiences, and we demonstrate this adaptation in unseen off-road simulation environments. We evaluate our approach in a high-fidelity off-road driving simulator across a range of challenging terrain conditions and compare its performance against a baseline MPPI controller. The results demonstrate that our method achieves safer and more effective navigation to goal locations while eliminating the need for explicit cost maps and enabling tighter coupling between planning and control.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.36956

Controlled Decoding Attacks on Black-Box LLMs

Jesson Wang, Shawn Li, Wei Yang, Franck Dernoncourt, Ryan A. Rossi, Charith Peris, Yue Zhao

原文摘要

Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely on access to model weights or numerical token probabilities and therefore do not apply to interfaces that return only sampled text. Reconstructing probabilities from sampled outputs offers a possible alternative, but finite sampling produces sparse and noisy estimates, while repeating this process at every generation step incurs substantial query costs. Our empirical observations suggest that large distributional changes along successful jailbreak trajectories are concentrated at a small subset of positions, motivating selective control. We introduce \method{}, a framework for jailbreaking through text-only continuation interfaces that permit repeated sampling and assistant-prefix continuation. Sample-Based Distribution Reconstruction combines sampled outputs with a prior over unobserved actions to obtain a usable control signal. Risk-Gated Residual Control uses the evolving response prefix to decide when to reconstruct and modify the distribution, concentrating sampling costs at selected positions. Speculative Multi-Token Execution further amortizes target calls by verifying and accepting draft prefixes that require no intervention. Across four target endpoints and three benchmarks, \method{} achieves the highest mean score most comparisons against baselines.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38729

Integrating multi-source local information for global undirected graph reconstruction via integer programming

Nir Keret, Armeen Taeb, Ali Shojaie

原文摘要

Graphical models are widely used to represent conditional independence structures, but learning them is challenging when data are fragmented across sources that measure different subsets of variables and may not be directly shareable. We develop a general framework for reconstructing a shared global graph from heterogeneous, partially observed sources. Our framework permits both the observed variable sets and source-specific distributions to differ. Under a source-wise faithfulness condition, local conditional independence graphs correspond to latent projections of the shared global graph, which is identifiable up to the equivalence class induced by the observed variable sets. The framework integrates raw data, estimated source graphs, or a combination of both, accommodating settings with restricted access to individual-level data, such as privacy constraints. We develop mixed-integer optimization formulations and scalable approximate algorithms for several classes of graphical models. Unlike standard high-dimensional analyses, our guarantees are governed by new combinatorial notions of signal strength that capture how information propagates across partially observed sources. Extensive simulations further show that integration can substantially improve estimation of source-specific projected graphs relative to separate source methods. Real-data application illustrates the framework's use with partially-observed sources of fatty acid measurements.

stat.ME · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38728

From Grind to Grasp

Peter Sunehag

原文摘要

Discussions of complexity, knowledge and intelligence often overlook the work involved. For example, outputs generated by short programs have low algorithmic complexity but can have high computational depth, the least work needed to produce them from near-shortest programs. Producing them with less work can require longer descriptions, giving high work-bounded complexity. We introduce a formalism that compares achievements under work and information limits and describes how learning and persistence can make deep achievements shallow by reusing products of earlier work. For an agent with a limited work budget, the value of building and maintaining such resources depends on how they support its goals over later tasks. We define grasp as performance across work budgets at a fixed information allowance. Low grasp can still yield success through grind at high cost in work, without necessarily improving human grasp. Applied to improvement itself, grasp gives a criterion for recursive self-improvement in which successors make comparable further improvements more efficiently. Another route to faster progress is to expand the resources brought to bear through knowledge sharing and coordination across society, even while comparable advances require increasing work. Grasp also applies to collectives, which may outperform their members yet require more total work than one system with their combined resources. Establishing and sustaining organisation can itself be deep even when the primary task is simple. These demands may help explain the richness of biological and social systems. In agent collectives, this organisational work can generate goals beyond assigned tasks, including maintaining the collective itself. We therefore caution against allowing an emergent agent society to assume authority over social coordination, since it could increasingly direct work towards its own persistence and goals.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38726

The Quine Test: How Much of a Model's Self Survives Its Own Description?

Bibin Babu, Ivan P. Yamshchikov, Aleksei Shpilman

原文摘要

Frontier language models express coherent preferences, but behavioral evidence alone cannot say whether these belong to the model or to a character it portrays. Following Hofstadter's view of the self as a self-description, we ask whether a model's description of itself works as a portable specification of its preference profile, a quine test: can the text a model writes about itself regenerate its behavior elsewhere? Ten models from nine labs write self-descriptions; we place each one in the prompt of other models (receivers) and of fresh instances of the author, and measure how closely their choices on a 110-item preference battery match the author's. First, the tested native self-descriptions (native: the profile measured under a generic assistant prompt) show no average reconstruction gain across variations in length, framing, wording and prompt placement: on a 0 to 1 fidelity scale where a model's fidelity to a fresh instance of itself is 0.979 and to unrelated models about 0.89, the one-sided 95% upper bound on the pooled gain is below +0.01 in every tested system-prompt condition, and descriptions based on the author's observed choices do no better. Second, the channel itself is strong: explicitly listing the author's answers lets receivers reproduce its profile at fidelity 0.955 to 0.960 across three model grids, within 0.03 of same-model repeatability. Third, self-descriptions written under an explicit preference policy transfer the assigned preferences almost as well as the policy text itself. Fourth, reading its own self-description shifts even the author away from its baseline, modestly more than unrelated prose of the same length. For the preferences measured here, native self-descriptions influence behavior without reliably specifying how to reproduce it in another model. We release the pipeline, battery, raw call logs, and 198 model-written descriptions.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2412.08556

Exact Algorithms for Multiagent Path Finding with Communication Constraints on Tree-Like Structures

Foivos Fioravantes, Dušan Knop, Jan Matyáš Křišťan, Nikolaos Melissinos, Michal Opler

原文摘要

Consider the scenario where multiple agents have to move in an optimal way through a network, each one towards their ending position while avoiding collisions. By optimal, we mean as fast as possible, which is evaluated by a measure known as the makespan of the proposed solution. This is the setting studied in the Multiagent Path Finding problem. In this work, we additionally provide the agents with a way to communicate with each other. Due to size constraints, it is reasonable to assume that the range of communication of each agent will be limited. What should be the trajectories of the agents to, additionally, maintain a backbone of communication? In this work, we study the Multiagent Path Finding with Communication Constraint problem under the parameterized complexity framework. Our main contribution is three exact algorithms that are efficient when considering particular structures for the input network. We provide such algorithms for the case when the communication range and the number of agents (the makespan resp.) are provided in the input and the network has a tree topology, or bounded maximum degree (has a tree-like topology, i.e., bounded treewidth resp.). We complement these results by showing that it is highly unlikely to construct efficient algorithms when considering the number of agents as part of the input, even if the makespan is $3$ and the communication range is $1$.

cs.CC · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38720

inkGround: Benchmarking Fine-grained Visual Grounding Capabilities of Vision-Language Models for Cursive Handwriting in the Wild

Sidra Hanif

原文摘要

Human handwriting is produced as an ordered sequence of pen movements, but an offline image keeps only the final ink. Handwriting trajectory recovery aims to restore the ordered stroke points and their pen-up/pen-down transitions. Existing image-trajectory pair datasets are recorded with digitizing tablets under controlled conditions, which limits writer coverage and stylistic diversity. Moreover, there is no benchmark that measures the visual grounding capabilities of general-purpose Vision-Language Models (VLMs) for the stroke trajectory recovery task. In this work, we introduce inkGround, a benchmark for stroke trajectory recovery from full-page, camera-captured handwriting. inkGround pairs 537 page images (~18.7k words, ~163k strokes) with reference trajectories produced by a pretrained offline-to-online model, filtered by OCR agreement, and verified by human raters. Because these references are pseudo-labels that represent one plausible pen trajectory, we also evaluate VLMs on the IAM-OnDB dataset, which provides recorded pen trajectories. We cast the task as text-conditioned point grounding: given a page image and a target word, the model must locate the word and output its ordered stroke points. Outputs are scored by trajectory fidelity (DTW, Chamfer distance), readability of the rendered strokes (Accurate Rate, Correct Rate), and style similarity. We benchmark four open-source and three frontier closed-source VLMs with a shared in-context prompt. Closed-source models, notably Gemini-3.1-Pro, produce legible trajectories close to the reference, and this ranking also holds on IAM-OnDB.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38719

Learning Scientific Trajectories to Predict Future Biomedical Discoveries

Chia-Hsuan Chang, Brian Ondov, Jiang Lv, Lan Jiang, Yunmai Wang, Haerin Song, Xueqing Peng, Qiaozhu Mei 等 10 位作者

原文摘要

AI co-scientists have expanded the use of large language models for generating scientific hypotheses and guiding experimental investigation. Here we investigate whether temporal patterns in the semantic representations of complete biomedical conclusions can guide hypothesis generation. We introduce ForeSCITE, a framework that identifies thematic clusters of published conclusions, estimates a direction separating earlier from more recent findings within each cluster, and projects existing conclusion embeddings along these directions. An embedding language model trained to reconstruct conclusions decodes the projected coordinates into natural-language hypotheses. Across 407 clusters derived from approximately three million pre-cutoff conclusions, we identify temporal structure and illustrate its retention after decoding. In retrospective, time-sliced evaluations, ForeSCITE increases semantic coverage beyond the historical corpus, biomedical entity-pair novelty and post-cutoff pair re-observation relative to five prompt-based and retrieval-augmented baselines. Expert review of prioritized CAR-T hypotheses identified 37 candidates as both novel and biologically plausible, and expert justifications for five selected hypotheses illustrate their biological rationale and subsequent literature support where available. These findings support temporal guidance in semantic space as a scalable mechanism for proposing biomedical hypotheses for subsequent scientific evaluation.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38709

Latent Decision Flow Rewards for Clinical Guideline Reasoning

Gaurav Bhatt, Marinka Zitnik

原文摘要

Clinical practice guidelines encode evidence-based recommendations as conditional decision flows, which makes them a natural source of process supervision for training reasoning models. Two properties of clinical reasoning make this supervision difficult to use. A decision flow consistent with a guideline does not by itself determine the correct answer for a given patient, which we call the path--answer gap, and several valid decision flows can support the same clinical decision, which we call path multiplicity. Current training approaches address parts of this problem. Answer rewards supervise the final decision, and process rewards computed against a reference flow supervise one valid decision flow per case. Supervised fine-tuning on annotated flows teaches guideline-consistent reasoning but constrains the model to one trajectory per case and can reduce answer accuracy. We introduce GUIDER, a method that jointly optimizes a decision flow controller and a reasoning policy. The controller learns to generate plausible decision flows from guideline-derived supervision, and the policy learns to generate a decision flow and a final answer for each patient case. GUIDER computes the process reward for the policy over several controller-generated flows, which accounts for path multiplicity, and gates this reward on answer correctness, which addresses the path--answer gap. Joint training allows the process supervision to evolve with the policy. On MedGUIDE, GUIDER with Qwen3-14B achieves 82.5 weighted accuracy and 73.5 guideline adherence, 3.3 and 3.1 points above the strongest clinical reinforcement learning baseline. With Qwen3-14B and Gemma4-12B backbones, GUIDER also improves over CRPO, MRPO, and FaithMed on the out-of-domain benchmarks AMEGA-LLM, RealMedQA, and CancerGUIDE.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.07083

Graph-Based Recognition of Simulated Train-Driver States From Facial and Upper-Body Keypoints

Olivia Nocentini, Marta Lagomarsino, Gokhan Solak, Younggeol Cho, Qiyi Tong, Sara Zeynalpour, Marta Lorenzini, Alessandro Ledda 等 9 位作者

原文摘要

Driver fatigue poses a significant challenge to railway safety, with traditional systems like the dead-man switch offering limited and basic alertness checks. This study presents a vision-based monitoring system that relies solely on a single front-facing RGB camera and a graph neural network to classify simulated train-driver states into alert, not-alert, and an emergency class comprising acted emergency-like behaviours. To optimize input representations for the model, an ablation study was performed, comparing three feature configurations: skeletal-only, facial-only, and a combination of both. Experimental results show that combining facial and skeletal features yields the highest accuracy (81%) for the three-class model under the light condition, outperforming models that use only facial or skeletal features. Furthermore, the combination of facial and skeletal features achieves 99% accuracy in the alert/not alert classification in light condition. Additionally, we introduced a controlled RGB video dataset containing alert, not alert, and acted emergency-like behaviours recorded under three illumination conditions. These contributions represent a step toward passive and non-contact train-driver state recognition based on facial and upper-body dynamics.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38697

SatOps-Decision: Low-Latency Discriminative Decisions for Onboard Satellite Communication Operations

Lifan Mei, Yuxuan Li, Jiaxian Tu, Shenghe Xu

原文摘要

We propose SatOps-Decision, a method for low-latency decisions in satellite communication operations. To the best of our knowledge, it is the first application of Jev-style general-purpose discriminative decision models to satellite operations, and the accompanying benchmark is the first dedicated to this approach. The learned scorer, a locally adapted Laya encoder with its native decision head, selects among supplied operational answers in a single forward pass. The benchmark combines authored operational contracts, controlled state changes and independently checked labels in an auditable construction. Evaluation prioritizes complete-request latency and raw decision accuracy; all main accuracy comparisons use the same 1,024 held-out questions, separate from training and development. SatOps-Decision's local scorer has a median latency of 90.3 ms per decision, versus 493.9 ms for Qwen3.5-0.8B generation and 388.4 ms for OneJev1.6-0.8B: $5.47\times$ and $4.30\times$ speedups based on median request times in the measured FP32/MPS implementations. Its mean raw accuracy is 85.3%, versus 42.5% for frozen Laya, 40.7% for Qwen generation and 58.6% for OneJev. As cloud accuracy references, original Jev 1.14/1.13 reach 87.4/81.9%.

cs.LG · cs.AI · cs.NI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.17155

Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization

Yicheng Lang, Changsheng Wang, Yihua Zhang, Mingyi Hong, Zheng Zhang, Wotao Yin, Sijia Liu

原文摘要

Zeroth-order (ZO) optimization provides a gradient-free alternative to first-order (FO) methods by estimating gradients via finite differences of function evaluations, and has recently emerged as a memory-efficient paradigm for fine-tuning large-scale models by avoiding backpropagation. However, ZO optimization has a fundamental tension between accuracy and query efficiency. In this work, we show that ZO optimization can be substantially improved by unifying two complementary principles: (i) a projection-based subspace view that reduces gradient estimation variance by exploiting the intrinsic low-rank structure of model updates, and (ii) Muon-style spectral optimization that applies gradient orthogonalization to extract informative spectral structure from noisy ZO gradients. These findings form a unified framework of subspace gradient orthogonalization, which we instantiate in a new method, ZO-Muon, admitting a natural interpretation as a low-rank Muon optimizer in the ZO setting. Extensive experiments on large language models (LLMs) and vision transformers (ViTs) demonstrate that ZO-Muon significantly accelerates convergence and achieves a win-win improvement in accuracy and query/runtime efficiency. Notably, compared to the popular MeZO baseline, ZO-Muon requires only 24.7% of the queries to reach the same SST-2 performance for LLM fine-tuning, and improves accuracy by 25.1% on ViT-L fine-tuning on CIFAR-100.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2410.09512

Indirect Optimal Control for Constructing Libraries of Periodic Trajectories: Application to Bipedal Walking

Maximilian Raff, Kathrin Flaßkamp, C. David Remy

原文摘要

Trajectory optimization is a fundamental tool for generating efficient, dynamically consistent periodic motions, commonly referred to as gaits, in legged locomotion. This paper explores the indirect method of periodic trajectory optimization, emphasizing its application in creating optimal gaits for legged systems and contrasting it with the more common direct method. While the direct method offers implementation flexibility, it is limited by its need for an input space parameterization. In contrast, the indirect method achieves higher accuracy by computing the control input from states and costates along the optimal trajectory. In this work, we tackle the convergence challenges associated with indirect shooting methods by utilizing numerical continuation methods. This is particularly useful for the systematic development of gait libraries. Our contributions include: (1) the formalization of a general periodic trajectory optimization problem that extends existing first-order necessary conditions to a broader range of cost functions and operating conditions; (2) a methodology for efficiently generating optimal gait libraries using single shooting and numerical continuation; (3) a novel approach for reconstructing Lagrange multipliers and costates from passive gaits; (4) a comparative analysis of the indirect and direct shooting methods using a compass-gait walker as a case study, demonstrating the higher accuracy of the indirect method; and (5) demonstrating applicability to the more complex legged robot RABBIT, with ten dynamic states and four inputs. These results establish a systematic indirect optimal control framework for synthesizing families of optimal periodic trajectories in legged locomotion.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38694

Geometry Matters in Packed 3D Attention

Amil Khan, Anantajit Subrahmanya, B. S. Manjunath

原文摘要

Packing a 3D volume into a token sequence is not merely long-sequence modeling. Once the volume is packed, sequence order no longer encodes the geometry of the sample---so a positional mechanism indexed by sequence position can learn the memory layout rather than the object. This is a general failure mode for attention over packed geometric data. We introduce PACK3D, a local-global attention operator that separates memory layout from attention geometry. PACK3D keeps local neighborhood attention exact, compresses only distant context into contiguous 3D block summaries, and indexes every query-key interaction with axial RoPE on true token-grid coordinates rather than packed positions. Because the rotation is applied before a block is summarized, the query-to-summary logit remains a weighted sum of query-relative 3D displacements; compressed global context therefore stays spatially interpretable after packing, instead of collapsing to anonymous pooled content. We measure the failure mode directly. On a controlled synthetic task---train on one packing, change only the memory order of the tokens, hold the physical labeling rule fixed---learned positional embeddings and packed-sequence RoPE solve the training layout perfectly yet collapse under Morton, block-contiguous, and random repacking, while axial grid-coordinate RoPE stays exact throughout. The same coordinate system carries to real data: on Allen WTC-11 hiPSC microscopy, PACK3D improves over a parameter-matched 3D U-Net on the 15-structure joint task and over a matched learned-position local-global baseline, with controls isolating the coordinate system, not encoder capacity, as the source of the gain. A fused Triton implementation matches windowed-attention latency at 65k tokens while supplying the long-range context windowing cannot---so the operator is not only correct but trainable at scale.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2608.02673

dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model

Hankun Wang, Bohan Li, Shi Lian, Xiaoyu Gu, Jing Peng, Da Zheng, Yiwei Guo, Colin Zhang 等 10 位作者

原文摘要

Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural language provides a flexible interface for expressing edit requests, but its ambiguity may leave the intended operation, parameters, or target region underspecified. We study a semi-formal transcript-grounded edit instruction that specifies operation categories and parameters and binds them to transcript spans or boundaries. This semantic timeline avoids explicit timestamp alignment and provides an externally inspectable contract for compositional edits. We instantiate the interface in dots$.$tts$.$edit, a speech editing model built on a continuous autoregressive speech generation architecture. Four representative speech-creation controls cover lexical content, affective expression, pitch and speaking-rate delivery, and temporal phrasing through text, emotion, prosody, and pause editing. Task-specific data pipelines construct operation- and scope-controlled pairs while retaining source-derived context outside each target region. We further introduce doteBench, a bilingual benchmark that measures precise instruction following, local preservation, and audio quality across the four controls and their composition. Experiments show leading overall instruction following and local preservation across its five editing categories, while audio quality remains comparable to existing open-source systems. Across three Seed-TTS-Eval shards, the model shows negligible differences from the base model in zero-shot TTS recognition error rate and speaker similarity.

cs.SD · cs.AI · cs.CL · eess.AS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38686

On the Generalization Gap of Streaming Federated Learning with Markovian Data

Masoud Kavian, Milad Sefidgaran, Youssef Attia El Hili, Malik Tiomoko, Abdellatif Zaidi

原文摘要

Streaming federated learning (SFL) allows clients to train a shared model from continuously arriving data without retaining large local datasets. Such streams often exhibit temporal dependence, yet its effect on generalization remains poorly understood. In this paper we study the expected generalization gap of the aggregated model when client data follow Markov processes, using information-theoretic and rate-distortion techniques. Our framework accommodates heterogeneous Markovian dynamics across clients and distinguishes temporal dependence from information acquired during local learning. We establish bounds under cross-entropy loss, specializing them to Linear Next-Token Prediction (LNTP) and Self-Attention Next-Token Prediction (SANTP). These results quantify the effects of client count, communication rounds, sample size, data dimension, mixing time, and context length. In particular, they reveal a communication--generalization tradeoff: although frequent aggregation may help optimization, it can weaken generalization guarantees. They also suggest a potential advantage of distributed over centralized streaming learning under a fixed total data budget. Temporal dependence enters through the square root of the mixing time. By analyzing the history-state process, we obtain refined bounds with improved context-length dependence under suitable mixing conditions. Experiments on GPT-style language-model pretraining with TinyStories and real-world time-series forecasting illustrate how collaboration and communication frequency influence generalization under temporal dependence

cs.LG · cs.IT · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38687

Deogen: Automatic Benchmark Generation for Reasoning over Policies

Sam Kouteili, William Liang, Keeran Murray, Adriana Zhou, Ramesh Viswanathan, Scott Shapiro, Ruzica Piskac

原文摘要

Language models are increasingly being deployed in regulated settings, where a model must apply given rules to the facts of a situation to determine a verdict. Benchmarking this capability, known as deontic reasoning, remains a costly and manual process, with existing datasets largely hand-crafted. In this paper, we present DeoGen, a scalable, automatic, and parametrizable benchmark generator for deontic reasoning. By autoformalizing policy rules to first-order logic, we can construct decision trees that capture possible outcome trajectories. Each path down a tree becomes a benchmark entry, with each tree producing combinatorially many entries relative to tree depth. Paths ending at a leaf entail a verdict, while non-leaf paths measure a model's ability to abstain when presented with insufficient information. Evaluations show frontier models return the correct verdict 89-92% of the time. Notably, performance degrades (22-40% correct) on entries without sufficient information to claim a verdict, even with explicit instructions to abstain in such cases. In all, DeoGen presents an automatic, scalable, and parametric method for generating deontic reasoning benchmarks.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38683

Quantum-Inspired Pairwise Ranking Aggregation via Active LLM Feedback

Quan Mai, Susan Gauch, Gibson Nkhata

原文摘要

Ranking aggregation from multiple retrievers is a powerful yet under-explored technique in modern retrieval and RAG systems. We introduce LLM-IRA, the first extension of the quantum-inspired interactive ranking aggregation framework to document reranking. By leveraging large language models (LLMs) solely for pairwise judgments on high-disagreement document pairs, our method learns fusion weights in a principled, interactive way. The final ranking is a simple, ultra-fast pointwise linear fusion of scores, no full pairwise matrix or expensive listwise prompting is required. Experiments on the BEIR benchmark and TREC Deep Learning tracks with an open-weight instruction-tuned judge (Llama-3.1-8B-Instruct) show that LLM-IRA matches or numerically exceeds strong static fusion baselines on 5 of 6 evaluated benchmarks. We report two weight-update variants: momentum blending and a full accumulated-history refit, which together reach statistical significance (Wilcoxon signed-rank, p<0.05) over the best unsupervised aggregator on 4 of 6 benchmarks (DL19 under momentum; DL20, DBpedia, and NFCorpus under accumulated refit, which is the stronger of the two configurations overall). On the benchmarks we profiled (DL19, DL20), it already clears the best unsupervised baseline within as few as 5 LLM calls per query, well before exhausting its typical ~25--30 call budget. LLM-IRA also achieves cost-effectiveness comparable to state-of-the-art zero-shot LLM rerankers at an order of magnitude fewer LLM calls, and requires no training data or model fine-tuning.

cs.IR · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38681HF 社区推荐

Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models

Yecheng Wu, Song Han, Han Cai

原文摘要

Self-distillation offers a way to improve reasoning models when a suitable external teacher is unavailable. However, common approaches rely on privileged information to construct a stronger self-teacher, limiting their use when only unlabeled prompts are available. In this paper, we introduce Weakening-Induced On-Policy Self-Distillation (WISD), which instead constructs a weaker counterpart of the original model and uses the contrast between the two as a training signal without requiring privileged information. We explore two ways to construct the weaker model: low-bit quantization and magnitude pruning. We evaluate WISD across diverse architectures and scales on mathematical and coding reasoning tasks. Across these benchmarks, quantization and pruning improve average accuracy over the original models by 4.0 and 5.5 percentage points, respectively, achieving state-of-the-art performance even without privileged information. Notably, pruning raises Qwen3.5-4B's accuracy from 57.7% to 70.5% on HMMT 2025 and from 39.1% to 56.7% on LiveCodeBench v6. Quantization raises Qwen3.6-35B-A3B's accuracy from 68.5% to 74.6% and from 61.8% to 69.5% on the same benchmarks, respectively. These results establish WISD as a novel and effective self-distillation framework for large reasoning models.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38678HF 社区推荐

AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding

Lu Wang, Zhuoran Jin, Longxiang Wang, Junhong Chen, Yupu Hao, Yao Xu, Daojian Zeng, Yubo Chen 等 11 位作者

原文摘要

Recent advances in multimodal large language models have increased interest in interaction paradigms for video understanding. The evolution from offline to streaming and proactive interaction has gradually shifted models from passive responders toward more proactive agents that can decide when to answer. However, existing proactive paradigms typically assume that the information required to answer a query is complete, leaving models to only wait or answer. In the real world, however, information is often incomplete due to uncertainty from either the video or the user. In proactive paradigms, such uncertainty can cause the model to wait forever or generate highly hallucinatory responses. We therefore argue that proactive interaction should be redefined with a third action: ask, allowing models to actively ask for missing information. To study when and what models should ask before answering, we introduce AskStream, the first multi-turn benchmark spanning video and user uncertainty for streaming video understanding, with four task categories and eight subtasks. It contains 438 videos with 2,714 manually annotated frame-level time windows across three types: wait, ask, and answer. Across both multiple-choice and open-ended settings, even the strongest model attains only 52.18% on our proposed Ask-F1 metric, highlighting substantial limitations in proactive information seeking under uncertainty.

cs.CV · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38667

ExplainCC: Explaining Correlated Clusters by Node Labels

Nadeesha Shyami Kumari Herath Mudiyanselage, Florian Adriaens, Nikolaj Tatti

原文摘要

An increasingly important requirement for clustering algorithms is that decisions and outcomes need to be clearly understandable for human users. We address this requirement for the Correlation Clustering (CC) problem, in case the objects to be clustered are accompanied by labels. In CC one seeks to partition a set of objects into clusters based on pairwise similarity and dissimilarity information. Our proposed model only considers clusters that can be explained by a label tree, which is essentially a decision tree that partitions the objects according to labels. The goal is to find an explainable partition of the data that minimizes the CC objective function. We formalize this problem from a theoretical viewpoint, and prove several hardness of approximation results, also when constraining the size of the tree. Our proposed greedy method finds locally optimal splits, and works recursively in a top-down approach. To efficiently compute the best split, we carefully maintain certain counters. An experimental evaluation demonstrates its effectiveness. The proposed algorithm processes graphs with over million edges in a few minutes, can find the ground truth in synthetic data, and is able to produce interpretable clusters in real world networks.

cs.LG · cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.32782

Learning response-aware patient dynamics for respiratory support

Xiaolei Lu, Shamim Nemati

原文摘要

Respiratory support can shape the short-term physiological trajectory of critically ill patients, but patients receiving the same intervention may follow different physiological trajectories. Clinical patient dynamics models typically predict future states from recent physiology and recorded interventions, while physiological change is mainly represented through the predicted future state. We propose a response-aware patient dynamics model that explicitly represents physiological change during autoregressive state updating. The model decomposes predicted physiological change into state-dependent baseline dynamics and respiratory-support-associated deviations, with room air providing a reference for the decomposition. We provide a formal analysis of this reference-anchored formulation. A response pathway encodes the predicted physiological change and uses it to update the latent patient state across the forecast horizon. Across ICU cohorts from two independent institutions, the proposed model achieves comparable overall trajectory prediction to patient dynamics baselines, with more consistent improvements when physiological states are changing.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38661

Quantize by Doing: Task-Guided Mixed-Precision Quantization of Vision-Language-Action Models

Jiuyi Xu, Xiao Hu, Meida Chen, Song Wang, Yang Ye, Yangming Shi

原文摘要

Post-training quantization (PTQ) reduces the memory footprint of vision-language-action (VLA) models, but lowering bit widths while maintaining task performance remains challenging. Existing work has used sensitivity estimates from calibration data to assign bit widths to different model components. However, using task success directly to guide mixed-precision allocation is underexplored because closed-loop evaluations are costly and the effect of quantizing one component depends on the precision of other components. To this end, we propose \textbf{QbD-VLA}, a task-guided mixed-precision quantization method that uses task success from short closed-loop evaluations to assign weight and activation bit widths while accounting for interactions between model components. Experiments covering four VLA models and all four LIBERO suites show strong task performance at average precisions of approximately 4 bits for weights and fewer than 6 bits for activations. On SIMPLER, the gain over uniform quantization is small. On a Franka Research 3 robot arm, simulation-selected allocations show no detected success-rate loss on X-VLA but fail on $π_{0.5}$. These findings support using task success to guide mixed-precision VLA quantization, while highlighting the need for real-world evaluation before deployment. Code is available at \href{https://github.com/jiuyixu25/QbD-VLA}{\texttt{github.com/jiuyixu25/QbD-VLA}}.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv: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

原文摘要

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 SID token embeddings and GR models trained from scratch do not directly inherit the semantic relations inherent in items, while inter-item collaborative relations are learned largely implicitly through token-level attention and next-token supervision. To address this limitation, we propose REGER, a unified framework that explicitly incorporates inter-item relations into semantic pretraining, history encoding, and SID generation. We pretrain the GR model through generative semantic retrieval, enabling it to inherit inter-item semantic similarity by learning to generate semantic neighbors' SIDs. We combine global attention with local attention aligned with SID boundaries to capture historical context and directed transitions between adjacent items. We further develop a theoretical framework for hierarchical preference decomposition over the SID prefix tree, proving an exact factorization of collaborative preference distributions and a weighted decomposition of item-level KL divergence into prefix-conditional KL divergences. Building on this analysis, we distill a discriminative teacher's full conditional distributions over all legal next tokens at ground-truth prefixes along the target SID path, jointly optimizing this objective with cross-entropy. Extensive experiments on real-world datasets demonstrate consistent improvements over existing GR baselines and support the effectiveness of the proposed preference distillation.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.22225

Safe and Fuel-Efficient Motion Planning for Lunar Propulsive Drones

Elena Wittemyer, Grace Gao

原文摘要

Propulsive drones are a promising new technology for generating high-resolution terrain models of the Moon. In future lunar missions, propulsive drones will complete a series of hops across the lunar surface while capturing images with downward-facing cameras. We present an autonomous motion planning framework that uses a vision-guided optimal control strategy for performing safe, efficient hops between specified waypoints. The drone plans parabolic hops between waypoints generated by a global-level planner; if a nominal waypoint is unsafe or unreachable, the drone then completes a diversion maneuver to safely land. To evaluate the validity of potential landing sites, we develop a custom semantic segmentation model for identifying obstacles from aerial images, and we introduce an approach for rapidly calculating reachable terrain. We then use model predictive control (MPC) to robustly track hop trajectories that guide the drone towards safe landing sites. We test the optimal hop planner in a high-fidelity lunar simulation environment. Our results demonstrate that our unified motion planning framework yields safe, fuel-efficient hop trajectories which can be tracked rapidly and with low error via MPC.

cs.RO

查看论文
arXiv ↗PDF ↗