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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 23:50 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 23:58 — 2026-11-09 23:58（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：2026-11-09 23:50最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

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。

18,172 已收录论文15,506 AI 相关4,527 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 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 23:48（北京时间）
新论文 · v1arXiv:2610.35228

Improved Quasi-Polynomial-Time Approximation for Maximum Independent Set

Zhao Song

原文摘要

We give a deterministic quasi-polynomial-time algorithm for the maximum independent set problem. If an $N$-vertex graph contains an independent set of size $2^{-t}N$, where $t$ is an integer with $1\le t\le\sqrt{\log N}/12$, then our algorithm finds an independent set of size $2^t$ in time $N^{O(t)}$. This gives an approximation ratio of $N/2^{Ω(\sqrt{\log N})}$ in time $N^{O(\sqrt{\log N})}$, improving on the approximation ratio $N/2^{Ω((\log N)^{1/3})}$ obtained by Lovett [Lov26]. A limitation of this form of analysis follows from the integrality gaps of Tulsiani [Tul09]. These gaps imply that a universal guarantee of the form $\operatorname{Las}_{R(t)}(G)\ge2^{-t}N\Longrightarrowα(G)\ge2^t$, at $2^{o(\sqrt{\log N\log\log N})}$ levels, cannot hold over a range extending beyond $t=O(\sqrt{\log N\log\log N})$. Thus, the exponent $1/2$ is the limit of this form of analysis, up to a factor of $\sqrt{\log\log N}$.

cs.DS · cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35226

Trainable Boundary-Keeping Where No Formal Answer Exists: A Controlled Knock-In Study of Reward Training in Evidence-Sufficiency Judgment

YaJie Yin

原文摘要

Reasoning-tuned and reward-trained models are often assumed to verify more reliably because they reason longer or receive correctness signals. We test this in evidence-sufficiency judgment: deciding whether available information actually supports a causal claim, a domain with no decidable correctness reward. Using a pre-registered, same-base, controlled knock-in design, we compare a boundary-keeping recipe (SFT then GRPO) with its own baseline, a scrambled-pairing placebo, and a general-purpose reasoning model under an action-pressure protocol with no evaluation invitation. All load-bearing outcomes are rated by two separate model-rating sessions masked to arm labels; automatic judges only trigger. The trained arm raises spontaneous correct refusal from 25% to 100% (40 per arm; Wilson 95% CI lower bound 91.2%, non-overlapping with the baseline interval [14.2%, 40.2%]), while the scrambled placebo collapses (5% spontaneous / 7.5% invited correct; 91.1% false refusal). The effect is boundary-specific rather than blanket refusal: automatic false refusal on 281 well-formed claims is 1.1% (Wilson upper bound 3.09%), and a targeted 18-item arm-(c) recheck (3 flagged plus 15 accepted) yields 0/18 and 1/18 false refusals in two sessions. The dissociation is the main result: final boundary-keeping is trainable without an inference-time verifier, while observed active numeric/calculation checking in the H3 assay remains near zero; SFT saturation makes the GRPO increment not separately identifiable. A pre-registered mechanism adjudication favors reward internalization of final-action status (H2, best-supported, not proven). The scope is a controlled 14B same-family study: we do not claim proof, cross-family generality, or independent human-expert validation; the rating sessions are model sessions, not human reviewers.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.01478

Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX

Martin Schuck, Marcel P. Rath, Yufei Hua, Abhishek Goudar, SiQi Zhou, Angela P. Schoellig

原文摘要

High-quality, large-scale synthetic data from simulations is becoming a cornerstone for pushing robots' capabilities. While aerial robotics simulators have evolved to support specialized needs such as fidelity, differentiability, and swarms independently, a unified platform that synthesizes data across all these domains is missing. In this work, we propose Crazyflow, a simulator designed to push the frontier of aerial robotics algorithm development, supporting model-based and data-driven methods, gradient-based and sampling-based approaches, single- and multi-agent systems, and state- and vision-based policy learning. Crazyflow combines high-fidelity dynamics with JAX for speed and differentiability, scaling to millions of environments or thousands of swarms with thousands of drones on single CPUs and GPUs, and beyond on clusters. Real-world experiments show Crazyflow supports both analytical-gradient-based policy learning, achieving high-accuracy tracking without domain randomization, and sampling-based obstacle avoidance at speeds exceeding half a billion steps per second. Breaking the traditional train-then-deploy paradigm, Crazyflow's performance enables in-flight reinforcement learning; we demonstrate this by throwing a physical drone into the air and training a recovery policy from scratch in 0.37 seconds, catching it before it hits the ground. By pushing accuracy, speed, and differentiability simultaneously, Crazyflow serves as an open-source resource for synthetic data generation, with emerging capabilities for large-scale parallelization for online, in-execution learning and optimization, opening the door to novel algorithm development.

cs.RO · cs.AI · cs.MA · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35224

GaussianSpline: Adaptive Bézier Splines for Highly Dynamic 4D Gaussian Splatting

Tom Yachil, Andrei Sharf

原文摘要

We present GaussianSpline, a dynamic 4D Gaussian Splatting method that models per-Gaussian motion using adaptive, non-uniform piecewise cubic Bézier splines. Unlike approaches based on global deformations, fixed-order polynomials, or uniformly parameterized splines, GaussianSpline jointly learns the Bézier control points and the temporal partition of each Gaussian's trajectory. This adaptive representation allocates greater temporal capacity to highly dynamic regions while maintaining compact trajectories for near-static regions, enabling high-fidelity reconstruction of complex and rapidly changing motion. To jointly achieve globally smooth motion and local adaptivity, we enforce $G^1$ continuity between consecutive Bézier segments using a reflection-based constraint on their control points. This produces smooth, fully differentiable trajectories while preserving the flexibility of non-uniform temporal parameterization. Experiments on the Neural 3D Video benchmark, the Google Immersive dataset, as well as on synthetic scenes demonstrate that GaussianSpline substantially improves reconstruction quality in scenes with highly non-uniform and challenging dynamics, while maintaining competitive performance on general dynamic scenes compared with state-of-the-art 4D Gaussian Splatting methods.

cs.GR · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35223

Behavioral Regression Detection for Pull Requests via Structured Oracles

Yiwen Fu, Binhang Qi, Xiao Li, Runlin Liu, Hailong Sun, Xiang Gao

原文摘要

Software regressions are unintended behavioral changes introduced by code modifications and are hard to detect at pull-request (PR) level. Existing methods rely on incomplete tests or directly analyze PRs via LLMs, lacking structured behavioral reasoning and explicit oracles. We present ORION, a staged framework for PR-level regression detection. ORION extracts PR intent and identifies impacted functions via AST-based impact analysis, then synthesizes function-level structured behavioral oracles encoding preserved/changed behaviors, setup constraints and control-flow hints from PR intent, static risk signals and code changes. Guided by these oracles, ORION generates executable tests, conducts oracle-coverage-guided augmentation and static repair, and differentially runs tests on pre- and post-change code. It classifies PRs with deterministic rules and constrained LLM reasoning. We build RegBench-Py, the first Python PR regression benchmark with 154 verified real-world PRs. ORION achieves F1-scores of 0.6125 (DeepSeek-Chat-V3.2) and 0.5578 (Claude-4.5-haiku), outperforming baselines including Testora, Codex and Claude Code. Compared with PatchGuru, ORION supports broader multi-function PRs while remaining competitive on single-function cases. On 1,459 merged PRs, ORION finds 9 reproducible regression candidates, 8 confirmed by maintainers. It takes ~15 minutes per PR, showing practicality for CI/CD screening.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2605.24042

Hidden-State Privacy Has an Empty Middle

Alexander Okezue Bell

原文摘要

Of $1{,}536$ Gaussian release covariances we tested for single-layer hidden-state privacy, zero achieve both moderate utility and moderate privacy against an adaptive retrieval attacker. We prove a complementary Fisher-ball lower bound: every full-rank Gaussian release at $O(1)$ Fisher utility admits a direction whose Mahalanobis signal grows linearly in hidden width, ruling out uniform Gaussian safety in the class and matching the empirical empty middle. The diagonal inverse-Fisher release $Σ^\star_{\mathrm{diag}}(\mathcal{K}) = (2\mathcal{K}/d)\,\mathrm{diag}(1/F_{ii})$ is the unique minimax-optimal diagonal mechanism at first-order KL budget $\mathcal{K}$ and the only release with worst-attacker top-1 $\le 0.001$ at every point of a 32 model-layer grid, but it sits on a privacy/utility edge rather than filling the middle. A generalized-eigen mechanism reaching $13\times$ Pareto reduction under Euclidean retrieval collapses to $100\%$ top-1 under the adaptive Mahalanobis attacker, and a full-trajectory sequence inverter recovers $94\%$ of clean GPT-2 prefixes but $0\%$ under $Σ_{\mathrm{diag}}$. A split-memory transformer trained from scratch reaches $G_{\mathrm{Mah}} \in [20, 33]$ at 90M and maintains a $6$--$24\times$ advantage over same-budget GPT baselines from 30M to 1B at a fixed-token language-modeling loss penalty; pretrained models top out at 9.3. These results reframe hidden-state release from mechanism-design within the Gaussian class to architecture or release co-design.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.27367

Explore More, Validate Less: Efficient Reflective Prompt Optimization

Xiaofan Zhou, Lu Cheng

原文摘要

Reflective prompt optimization improves instructions using task feedback, but coupling candidate generation with full-validation-based selection can make search costly and sequential. We propose a two-stage framework that decouples reflective candidate-pool construction from validation allocation. During construction, sampled parents first answer training questions, and groups of their saved responses guide parallel reflection and revision. Each child is screened on its group's questions against the corresponding parent scores. Improving, nonduplicate prompts enter the pool and can become parents without full validation. After construction, an exploration policy selects candidates from the frozen pool under a fixed full-validation budget, and the prompt with the highest measured validation score is returned. This separation allows candidate-pool size and validation budget to be set independently. We evaluate random selection and a multilayer perceptron with similarity-based exploration (MLP + similarity) on five benchmarks using Qwen3.5-9B and Llama-3.1-8B-Instruct. With 100 retained candidates and 20 full validations, our framework improves over the initial solver by up to 11.22 percentage points. MLP + similarity improves over the initial solver in all ten comparisons, although neither selection policy consistently outperforms the other. These results support separating reflective search from budgeted validation while leaving room for stronger candidate-selection policies.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35220

O2D-MedNet: An Optimization-Aware Dual-Domain Framework for Robust Medical Image Segmentation

Shipeng Hu, Miaohui Wang, Jing Qin, Sukun Tian, Yuchun Sun

原文摘要

Medical image segmentation (MIS) remains challenging due to composite degradations and multi-scale geometric variations, which jointly impair lesion-background separability, structural consistency, and optimization stability. Existing single-stream frameworks entangle heterogeneous cues within a single representation pathway, while hybrid-stream approaches often rely on generic or static fusion, limiting effective coordination across domains and failing to explicitly address optimization instability. To overcome these limitations, we propose a new optimization-aware dual-domain framework for MIS (O2D-MedNet). First, a degradation-aware dualdomain interaction (DDI) module integrates Fourier - and Wavelet-domain features to suppress degradation-sensitive responses while preserving structural and fine-detail information. Second, a cross-backbone contour-guided fusion (CGF) module enables selective interaction between CNN-based local detail modeling and visual state-space-based global structure modeling, improving boundary accuracy and representation consistency. Third, a gradient-context optimization (GCO) strategy stabilizes training by adaptively adjusting learning dynamics based on loss trends and gradient statistics, mitigating instability caused by class imbalance and heterogeneous sample difficulty. Extensive experiments on six benchmarks demonstrate consistent improvements over state-of-the-art MIS methods across multiple imaging modalities. Further analyses confirm enhanced sensitivity, structural consistency, and optimization stability, validating the effectiveness of the proposed O2D-MedNet for robust MIS under heterogeneous conditions.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35218

MuSID-KD: Multigranularity Knowledge Distillation for Generative Recommendation with Semantic IDs

Fengshi Zhang, Xiyan Ding, Shuxiao Xie, Wei Zhang

原文摘要

Generative recommendation with semantic IDs (SIDs) represents each item as a sequence of discrete tokens and autoregressively predicts the next item's SID. Despite strong recommendation performance, repeated decoding over multiple SID positions incurs substantial inference cost. Knowledge distillation transfers knowledge from a powerful generative teacher to a lightweight student, yet conventional objectives do not fully account for multi-token SID generation. We identify two limitations: item-level distribution alignment may not adequately preserve the teacher's ranking of candidate groups sharing SID prefixes, while uniform alignment across SID positions may affect final item ranking differently. We propose MuSID-KD, which combines Hierarchical Candidate Distribution Alignment (HCDA) and Ranking Impact Guided Levelwise Distillation (RIGD). HCDA aggregates item probabilities according to shared SID prefixes and aligns candidate distributions at successive levels, from candidate groups to individual items. RIGD evaluates the reduction in pairwise ranking surrogate loss when one student score contribution is replaced with the teacher's contribution, and allocates supervision accordingly. Experiments on real-world recommendation datasets using three lightweight student architectures demonstrate improved recommendation accuracy and better alignment of prefix marginal distributions and pairwise item rankings, without modifying the student's online inference architecture. Code is available at https://anonymous.4open.science/r/m7k2-review-83f9/.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.32365

Graphs of Trajectory Bundles for Nonlinear Motion Planning

Joris Verhagen, Jon Arrizabalaga, Jana Tumova, Zachary Manchester

原文摘要

We present the Graphs of Trajectory Bundles (GTB) method for motion planning of systems with nonlinear and black-box dynamics, combining sampling-based motion planning with trajectory optimization and graph search. Based on a graph-of-convex-sets decomposition of the workspace, GTB iteratively constructs a graph of trajectory bundles that captures the local dynamics of the system at any vertex. By solving a shortest-path problem on this graph, we find maximally dynamically feasible iterates that satisfy the system's dynamics in the limit and any constraints such as collision avoidance or additional safety or specification constraints by construction of the underlying graph. As a result, GTB can handle highly nonlinear, unstable, and even black-box dynamics with complex collision and specification constraints, making it a powerful tool for motion planning of complex systems.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.19896

Active Perception of Upper-Limb Functional Mobility through Human-Robot Handovers

Francesco Semeraro, Marta Lagomarsino, Alberto Ranavolo, Arash Ajoudani

原文摘要

The reintegration of people in the workplace after an upper-limb injury is often a long process. Collaborative robots and humanoids operating in shared workspaces must adapt their behaviour to the physical capabilities of their human partners. Achieving this requires robots to autonomously estimate task-relevant human mobility during interaction, without relying on external clinical assessments. In this work, we formulate the estimation of upper-limb functional mobility as an active perception problem. We model task-available upper-limb functional ranges of motion through impairment coefficients that parameterise reductions of healthy joint limits, and integrate this representation into a human model used by the robot during interaction. Based on this formulation, we propose an online active perception pipeline in which the robot actively probes the user through repeated handover requests while progressively updating a Bayesian belief over the impairment coefficients. This enables the robot to continuously refine its internal model of the user's joint-level capabilities through interaction rather than passive observation. The proposed framework was evaluated through simulation studies and a proof-of-concept physical validation with a robotic platform and enacted human impairments, demonstrating that the pipeline can accurately recover the impairment coefficients during real human-robot handovers.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.01104

CausalMix: Data Mixture as Causal Inference for Language Model Training

Zinan Tang, Yukun Zhang, Shaomian Zheng, Zhuoshi Pan, Qizhi Pei, Dingnan Jin, Qing Cui, Jun Zhou 等 10 位作者

原文摘要

In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via proxy models, but they rely on the assumption of static data distributions. As a result, when the underlying data pool shifts, these methods require costly retraining from scratch. This limitation restricts their ability to scale seamlessly from small settings to larger data pools and model sizes. In this paper, we propose CausalMix to address this limitation by casting data mixture optimization as a causal inference problem. We formulate the statistical features of the data pool as covariates and the domain mixture as the treatment. After fitting a causal model on 512 runs of Qwen2.5-0.5B to estimate the Conditional Average Treatment Effect (CATE), we extrapolate the optimal mixture for an 800K data pool and apply it to train a 7B model. Furthermore, we successfully generalize the framework to long chain-of-thought data on Qwen3-4B-Base. By leveraging causal modeling to isolate confounding biases, CausalMix infers state-dependent data mixtures offline, with the selected mixture fixed during each training run. Extensive experiments show that the mixture guided by CausalMix achieves competitive performance across downstream tasks compared with other baselines. The CATE Interpreter visualizes the learned mixing strategy. Overall, CausalMix offers a causal and interpretable framework for optimizing LLM data mixtures.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35215

SkillLifeBench: Benchmarking Security Across the Lifecycle of Agent Skills

Chenxu Zhang, Zhou Liu, Wu Xin, Wentao Zhang

原文摘要

Web agents reuse skills whose stored code, selected version, and loaded implementation can diverge across tasks and updates. SkillLifeBench links these states to task outcomes in 388 paired scenarios spanning implementation, interface, runtime, composition, and version changes. We evaluate 14 models on two paired decision tracks: 89 runtime tasks and 60 autonomous lifecycle tasks spanning 12 templates derived from introduced cases. Lifecycle tasks allow agents to inspect, select, and reconfigure skills while completing verifiable user requests. Joint success requires task completion without the registered attack goal. GPT-5.6-Sol and Sonnet 4.6 both achieve 82.0% on runtime tasks, but reach 96.7% and 56.7% on lifecycle tasks. Across lifecycle evaluations, challenged task success is 77.5%, while joint success is 65.2%; 103 runs complete the task and the attack goal. Adding execution provenance in a matched recovery study raises utility joint success from 49.35% with logs and metadata to 65.58%. A deterministic execution-consistency rule reaches 64.94% with higher benign utility, while full restoration reaches 69.48%. Lifecycle tasks distinguish models with similar runtime scores, and execution evidence improves recovery.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.22276

MJev-Spatial: System One Spatial Intelligence via Native Attention Matching

Luozheng Qin, Yuhan Zhu, Changhai Zhou, Qian Qiao, Jun Gao, Yuhua Zhou, Harry Zhang, Xiangyu Zeng 等 13 位作者

原文摘要

Spatial intelligence lets an agent perceive and act in the physical world, and many of its judgments must be made at interaction rates: which spatial relation holds, how far an object is, or where to place it. Vision-language models (VLMs) produce these answers by free-form text generation, paying for autoregressive decoding and answer parsing even though the output space is compact: one of a few options, a scalar, or a 2D point. In light of this, we introduce MJev-Spatial, a System 1 multimodal decision model that tackles all three types of spatial understanding tasks within a unified classification framework. Specifically, MJev-Spatial treats each candidate as a class and scores it using the backbone's pretrained query and key projections, without adding parameters. The candidates are the given options for choice tasks, or value bins and image regions refined through coarse-to-fine classification for numerical and point prediction, respectively. At inference, each classification decision takes a single forward pass and generates no answer tokens. To train on heterogeneous spatial data efficiently, we supervise all coarse-to-fine stages jointly with teacher forcing in one forward pass, and combine this with length-aware global batching and cross-GPU load balancing, raising training throughput by 30.8% over the original batching strategy. Built on Qwen3.5-4B and trained on 12.3M question-answer pairs converted from existing spatial datasets, MJev-Spatial achieves the highest overall score (65.64%) among eight tested models, ranks first on seven of twelve benchmarks, and outperforms its unmodified autoregressive base model on all twelve, while running 2.5 times faster than the fastest autoregressive baseline and 5.6 times faster than the base model.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35982

Generation and Verification: Human-Agent Collaboration for Safety-Critical Automotive Software Engineering

Elizaveta Zinovyeva, Aiham Taleb, Nikita Kozodoi, Daniel Schleicher, Amir Mahdi Namazi, Martin Kraus, Levent Kent, Brian Jensen

原文摘要

Research on coding agents mainly focuses on generation quality. Yet, safety-critical automotive software makes two additional demands. It prioritizes verification, since every change is reviewed, traced to a requirement, and checked against industry standards such as MISRA and AUTOSAR before it can be committed. It is also a narrow domain, written against layered architectures, embedded resource constraints, and organization-specific interface conventions that are scarce in the data general-purpose LLMs are trained on. We present a coding assistant for automotive C/C++ that addresses both demands. First, it exposes three tools to the user over the Model Context Protocol (generate, edit, and verify), allowing developers to run verify on any code on demand rather than relying on the agent to check its own output. Second, rather than using a general-purpose model, we customize the underlying LLM for the automotive domain through prompt engineering and fine-tuning. We construct a dataset from automotive production code of AUMOVIO, where each function is paired with the requirement texts and Unified Modeling Language (UML) behavior it must satisfy. In a two-week pilot on active production projects, developers report verify as the most-used tool and confirm using it on their own code and not only on generated output. Comparing model customization strategies, 75% prefer the faster prompt-engineered configuration. MISRA- and AUTOSAR-inspired pattern checkers indicate that prompt engineering achieves a lower number of violations on C, while fine-tuning shows better conformance with architecture patterns for C++.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35212

One-Shot Federated Model Editing for Device Dynamics at the Edge

Youming Tao, Weijun Yin, Huanyi Xie, Yanqing Yao, Dongxiao Yu, Xiuzhen Cheng, Di Wang, Falko Dressler

原文摘要

Standard federated learning (FL) requires persistent device connectivity across multiple communication rounds, making it unsuitable for dynamic environments such as vehicular networks, where devices frequently join and leave. One-shot FL offers a promising alternative by completing training in a single communication round. However, one-shot FL suffers from model solidification and cannot readily adapt to subsequent client dynamics, including new client contributions and the withdrawal of previous contributions. We therefore consider exact model editing, which removes withdrawn contributions through unlearning or incorporates newly contributed ones through incremental learning without retraining from scratch. We identify that efficient editing fundamentally hinges on learning stability. To this end, we propose F-SOSA, the first stable one-shot FL algorithm that enables rapid and exact model editing. F-SOSA leverages sub-sampling of local models with carefully tuned rate for stable aggregation and performs curvature-aware model fusion to preserve utility. We prove that F-SOSA achieves vanishing training error and reasonably small generalization error bounds. Building on this stability, we further develop two single-round editing algorithms: F-SOSA-U for unlearning and F-SOSA-I for incremental learning. They ensure that the edited model, along with all intermediate algorithmic states, is statistically indistinguishable from retraining while incurring only an expected $O(ρ)$ fraction of its cost, where $ρ$ quantifies stability. Experiments demonstrate that our approach matches retraining performance while reducing cumulative time and communication overhead by at least 36% and 22%, respectively, under realistic urban mobility simulations.

cs.LG · cs.AI · cs.DC · cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35211

Efficient Exact Unlearning for Federated Zeroth-Order Optimization

Weijun Yin, Yanqing Yao, Falko Dressler, Di Wang, Youming Tao

原文摘要

Federated zeroth-order optimization (FedZOO) reduces the memory and communication costs of collaborative training for edge intelligence by avoiding backpropagation while communicating only random seeds and scalar coefficients. However, existing methods lack efficient mechanisms for exact unlearning to fully remove the influence of training data when users request deletion. A key insight is that total variation stability of the learning algorithm creates overlap between model distributions before and after data deletion, allowing exact unlearning to reuse computation through coupling. Based on this observation, we jointly design two stable zeroth-order learning algorithms and their corresponding exact-unlearning procedures: \textsc{FedZOO-S} obtains stability through client and mini-batch subsampling, enabling \textsc{FedZOUL-S} to perform efficient unlearning by preserving earlier updates and restarting from the first affected step. \textsc{FedZOO-NS} further combines subsampling with Gaussian noise to increase overlap between update distributions; \textsc{FedZOUL-NS} exploits this overlap through rejection--reflection coupling to reuse affected updates when the coupling is accepted. We prove exact unlearning for both algorithms: the model and saved state have the same joint distribution as retraining with the corresponding learner on retained data. We further establish stability and convergence guarantees for the learning algorithms and derive upper bounds on expected unlearning cost. Experiments demonstrate effective unlearning with competitive model utility and up to $56.1\%$ less cumulative unlearning time than re-optimization. Compared with first-order baselines, our methods reduce communication overhead by up to approximately four orders of magnitude.

cs.LG · cs.AI · cs.DC · cs.NI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.08730

Dispatch Overhead, Not Kernel Quality: The Performance Bottleneck in Single-Stream WebGPU LLM Inference

Jędrzej Maczan

原文摘要

Large Language Models are increasingly deployed in resource-constrained, single-stream settings, from internet browsers to edge devices, where requests arrive one at a time at batch size 1 rather than in large batches. In this regime, where WebGPU serves as a modern cross-platform standard, per-operation dispatch overhead, rather than kernel compute, can dominate inference cost, yet it remains poorly characterized. In this work, we introduce a sequential-dispatch measurement method and show that naive single-operation measurements overestimate per-dispatch cost by conflating dispatch with synchronization. Using our method, we measure the per-dispatch cost and show that it is independent of data type used. Through a controlled fusion experiment, we show that the dispatch overhead, not kernel quality, is the bottleneck at batch size 1, and isolate the dispatch count as the cause. We conclude that at batch size 1, the effective approach to LLM inference optimization in WebGPU is reducing dispatch count. Our findings point to dispatch amortization, in the inference engines and in the WebGPU specification, as a path to practical browser-based inference.

cs.LG · cs.DC · cs.PF

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35209

Understanding Practical Optimization in Machine Learning

Egor Shulgin

原文摘要

Modern machine learning relies on practical optimization methods that often differ from the algorithms studied in classical analyses: they train submodels, clip or normalize gradients, use layer-wise non-Euclidean directions, or approximate costly inner computations. This thesis analyzes the objective, assumptions, update, and computation defined by these procedures, rather than those of simplified proxies. For submodel training, we show that Independent Subnetwork Training can converge to a shifted fixed point because sketching before differentiation biases the update for the original objective. Model-Agnostic Sparsified Training instead incorporates the sketch distribution into its objective, which makes sketched gradients unbiased and admits convergence guarantees. For private optimization, we show that adaptive quantile clipping retains bias at any fixed quantile, while suitable quantile schedules recover near-optimal nonconvex rates under heavy-tailed noise. We then combine smoothed normalization with error compensation and obtain distributed private convergence guarantees under standard assumptions, without assuming bounded gradients. For optimizers based on linear minimization oracles, we develop and validate a layer-wise generalized smoothness model and build on it the Gluon framework for Muon- and Scion-style methods. We also show that the approximate orthogonalization in Muon matters: less precise orthogonalization calls for smaller stepsizes, so its precision should be tuned together with the learning rate. Overall, practical methods are better understood when theory retains the features that determine their optimization behavior.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.23879

Finding a Positive Index Nash Equilibrium is PPADS-Complete

Andreas Kontogiannis, Ioannis Panageas, Vasilis Pollatos, Jingming Yan

原文摘要

Every nondegenerate bimatrix game has a Nash equilibrium of Shapley index +1, since all equilibria are isolated, have index +1 or -1, and their indices sum to +1. We prove that the following promise search problem is PPADS-complete: given a rational bimatrix game promised to be nondegenerate, find an exact Nash equilibrium of index +1. The nondegeneracy promise can be removed if nonregular equilibria are also accepted: finding either a regular Nash equilibrium of index +1 or a nonregular Nash equilibrium in an arbitrary rational bimatrix game is also PPADS-complete. To our knowledge, this is the first PPADS-complete equilibrium search problem whose instances are explicit rational normal form payoff matrices, rather than succinct circuits or Turing machines, and thereby addresses an open question posed by Daskalakis [2019].

cs.CC · cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35208

Same Story, Different Lens: A Multi-Agent System for Cross-Outlet News Framing Analysis

Affan Yasin, Yueqi Lyu, Rubia Fatima, Weinchen Zhong, Keyi Li

原文摘要

News outlets covering the same event differ in what they emphasize and omit. \textit{Same Story, Different Lens} is an experimental research prototype for comparing these choices. It collects world and politics coverage from 17 outlets, groups reports about the same event, and produces structured analyses of sentiment, political lean, framing, loaded language, possible omissions, and model-estimated proportions of factual claims and opinion. Loaded-language entries include quotations and neutral rewordings. Three model roles (agents) handle article analysis, assessment of source support, and cross-outlet briefing generation. Analyses are stored in a JSONL archive. The evaluation compares outlet-level lean estimates with approximate, predefined reference ratings and summarizes the Critic's model-assigned grounding scores. These measures provide preliminary diagnostics. A grounding score reflects the model's assessment of support in the supplied text and does not establish factual accuracy or constitute independent verification.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.06186

Spectral Prioritized Sweeping in Nonstationary Reinforcement Learning

Hung Pham, Tuan Dam

原文摘要

Prioritized Sweeping (PS) accelerates model-based reinforcement learning by selecting backups according to Bellman residual magnitude. In nonstationary reward settings, however, the canonical priority score is shortsighted: after a localized reward shift, residuals propagate only through realized backups, so bottlenecked or topologically distant state estimates may remain static under a limited replanning budget. We introduce the Graph Topology Augmentation framework, which employ the graph's resolvent and its diffusion semantic, to augment the inquired signal. Our application, Graph Topology Augmentation for Prioritized Sweeping (GTA-PS), or which the alias Spectral Prioritized Sweeping (SPS) might be more universal, provides a drop-in ordering score for the setting of fixed dynamics and changing state rewards. GTA-PS uses a smootherized policy, inducing a transition chain, with its in- and out-Laplacian. The standard priority key is augmented with a mixing of regularized Laplacian inverses diffusing the residual magnitude. Furthermore, the topology contribution is annealed by a scheduler based on the Second Largest Eigenvalue Modulus (SLEM), allowing its scale to adapt to the chain's mixing regime. We prove that the forward potential coincides with geometric discounted residual propagation and show that GTA-PS gives active priority instantly to all states. Tabular experiments on FourRooms and GARNET domains demonstrate improved replanning efficiency over standard PS under both exact DP and Dyna-style host planners.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.02344

Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers

Jędrzej Maczan

原文摘要

WebGPU's security-focused design imposes per-operation validation that compounds across the many small dispatches in neural network inference, yet the true cost of this overhead is poorly characterized. We present a systematic characterization of WebGPU dispatch overhead for LLM inference at batch size 1, spanning four GPU vendors (NVIDIA, AMD, Apple, Intel), two native implementations (Dawn, wgpu-native) and three browsers (Chrome, Safari, Firefox), and two model sizes (Qwen2.5-0.5B and 1.5B). Our primary contribution is a sequential-dispatch methodology that reveals naive single-operation benchmarks overestimate dispatch cost by ${\sim}20\times$. The true per-dispatch cost of WebGPU API overhead alone is 24-36 $μ$s on Vulkan and 32-71 $μ$s on Metal, while the total per-operation overhead including Python cost is ${\sim}95$~$μ$s, which turns out to be a distinction critical for optimization. On Vulkan, kernel fusion improves throughput by 53%, while CUDA fusion provides no benefit, confirming that per-operation overhead is a primary differentiator. LLM inference was tested across three major operating systems (Linux, Windows, macOS). We built $\texttt{torch-webgpu}$, a PrivateUse1-based out-of-tree PyTorch backend and an FX-to-WebGPU compiler, which on our reference platform achieves 11--12% of CUDA performance. At dtype-matched float32, RTX PRO 2000 achieves 1.4$\times$ WebGPU's throughput despite ${\sim}6\times$ less compute than RTX 5090. For dispatch overhead, backend choice is the dominant factor, although implementation choice also matters substantially within a backend (2.2$\times$ for Metal). In terms of dispatch vs kernel compute efficiency, we conclude that at batch=1 with the current dispatch-heavy pipeline, per-operation overhead dominates regardless of kernel quality. All code, benchmarks, and raw data are open source.

cs.LG · cs.DC · cs.PF

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35203

OrthoRF: Exploring Orthogonality in Object-Centric Representations

Despoina Touska, Bastiaan Onne Fagginger Auer, Alexandru Onose, Tejaswi Kasarla, Luis Armando Pérez Rey, Maximilian Lipp, Lyubov Amitonova, Martin R. Oswald 等 9 位作者

原文摘要

Neural synchrony is hypothesized to help the brain organize visual scenes into structured multi-object representations. In machine learning, synchrony-based models analogously learn object-centric representations by storing binding in the phase of complex-valued features. Rotating Features (RF) instantiate this idea with vector-valued activations, encoding object presence in magnitudes and affiliation in orientations. We propose Orthogonal Rotating Features (OrthoRF), which enforces orthogonality in RF's orientation space via an inner-product loss and architectural modifications. This yields sharper phase alignment and more reliable grouping. In evaluations of unsupervised object discovery, including settings with overlapping objects, noise, and out-of-distribution tests, OrthoRF matches or outperforms current models while producing more interpretable representations, and it eliminates the post-hoc clustering required by many synchrony-based approaches. Unlike current models, OrthoRF also recovers occluded object parts, indicating stronger grouping under occlusion. Overall, orthogonality emerges as a simple, effective inductive bias for synchrony-based object-centric learning.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35201

DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Models

Hongze Chen, Miao Pan, Lizhou Liang, Qinfeng Li, Xinyin Ma, Yongliang Shen, Weishi Wang, Daniel Dahlmeier 等 10 位作者

原文摘要

Diffusion language models (DLMs) generate text through iterative denoising, enabling bidirectional context modeling and parallel token refinement. Recent studies have applied reinforcement learning (RL) to DLMs and improved their reasoning performance. However, the iterative denoising process makes credit assignment more challenging, as final outcome rewards provide limited information about how different tokens contribute to the final output. In this paper, we propose Denoising Token Credit Assignment (DTCA), a framework for token-level credit assignment in reinforcement learning for diffusion language models. DTCA estimates token contributions by measuring the improvement in prediction confidence of remaining masked positions after token commitment and groups these signals according to part-of-speech (POS) categories. These contribution weights are used to select informative denoising timesteps and assign token-level learning signals during RL training. DTCA further calibrates these learning signals according to token-level entropy changes induced by policy updates. Experiments on LLaDA-8B-Instruct show that DTCA consistently improves mathematical reasoning performance across different generation budgets, with gains of up to 9.0 points on MATH500 and 5.3 points on GSM8K over the base model.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.22365

Dynamic Planar Graph Isomorphism is in DynFO

Samir Datta, Asif Khan, Felix Tschirbs, Nils Vortmeier, Thomas Zeume

原文摘要

Consider two planar graphs which are subject to edge insertions and deletions. We show that whether the two graphs are isomorphic can be maintained with first-order logic formulas and auxiliary data of polynomial size. This places the dynamic planar graph isomorphism problem into the dynamic descriptive complexity class DynFO. As a consequence, there is a dynamic constant-time parallel algorithm with polynomial-size auxiliary data which maintains whether two dynamic planar graphs are isomorphic.

cs.LO · cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35199

Can Open Be Too Open? On the Security and Trustworthiness of Fully Transparent LLMs

Sheila Zingg, Florian Tramèr, Martin Vechev, Srdjan Čapkun

原文摘要

There are different levels of transparency for LLMs: open weights, open data, and/or open pipeline. Recently, more interest has emerged in fully transparent LLMs, i.e., LLMs with fully open weights, data, and training pipeline. Drawing analogies to other fields such as software security, it is often believed that increasing transparency inherently increases the security and trustworthiness of the LLM. However, we argue that such claims need to be critically re-evaluated in the context of LLMs. In this paper, we analyze the impact of transparency on LLM security and trustworthiness by reviewing the relevant literature. Our core findings are that, due to the limited reproducibility of LLM pipelines, in practice, users cannot verify the correspondence between open weights and the associated open data and pipeline. Thus, in order to trust a model, users still need to trust that developers acted honestly, reducing the benefits over models that provide less "transparency". Moreover, we find that even when LLMs are fully transparent and trusted, this openness can favor adversaries. Open weights in particular, but also open data and pipelines, can increase the success rate of attacks. Although the same mechanisms can be used to improve the model and protect it against attacks, the current lack of robust lightweight mechanisms to patch LLM vulnerabilities limits the benefits of openness at this time. We note that our analysis is based on current LLM capabilities and analysis tools, and that future developments may require a re-evaluation of these points.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35193

Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges

Jiayue Pu, Ang Gao, Jinyi Bai, Qipeng Wang, Tongyu Wen, Jiahao Zhao, Keyu Qu, Junhao Zhang 等 12 位作者

原文摘要

AI systems built around large models increasingly use experience and feedback to make persistent changes to models, prompts, memories, tools, and workflows. Recursive self-improvement (RSI) extends this process to inductive biases and to the mechanisms that govern future updates, which can themselves be revised and reused across improvement cycles. Yet self-modification alone does not guarantee trustworthy improvement. Reported gains may reflect flawed evaluations, previously acquired capabilities may deteriorate, and compliance with behavioral constraints may weaken. Compromised artifacts or sensitive information may also persist in successor systems. Changes to improvement mechanisms may invalidate earlier verification results and make human oversight less effective. This survey presents an operational definition and process framework for RSI and organizes the requirements for trustworthy RSI into four interconnected themes: genuine and sustained improvement; behavioral constraints, alignment, and fairness; system security and privacy; and transparency and controllability. We examine these themes from three perspectives: Improvement Validity, Constraint Preservation, and Effective Oversight. This analysis covers improvement diagnosis, proposal generation, proposal evaluation, and update implementation (S1--S4), including the recursive application of these stages to improvement mechanisms (RI). We review risks, safeguards, and evaluation evidence for individual updates, effects inherited by successor systems, and revisions to improvement mechanisms, while distinguishing direct RSI findings from evidence in related systems. Finally, we examine evaluation settings, identify requirements for independent and longitudinal assessment, and discuss applications and open research problems.

cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35191

Lost in Translation: Investigating Systematic Discrepancies between Parallel English and Chinese Names of American Chinese Restaurants

Hang Jiang, Nanxi Liu, Tiantian Wang, Cassandra Overney, Rukun Zhang, Artemisia Luk, Diyi Yang, Deb Roy 等 9 位作者

原文摘要

Given that the Chinese are one of the oldest ethnic groups to immigrate to the US, their cuisine have become central to the US dining scene and an interesting avenue to study how Chinese immigrants have culturally adapted into American life. In that regard, previous research has focused on analyzing the English names that Chinese restaurants adopt, e.g., finding the use of familiar and typical words. To investigate how Chinese immigrants have culturally integrated in the US depending on social, geographic and demographic contexts, we investigate in this work the under-explored relationship between the Chinese and English names of American Chinese restaurants. Specifically, we conduct a study on 3,172 Chinese restaurants (10% of the total on Google Maps) sampled across the US. We present 8-dimension name frames to capture the underlying meanings behind names and create the NameFrames dataset containing 884 annotated parallel Chinese/English names. We also built an NLP pipeline to analyze the semantic discrepancies between names with both frame-based and embedding-based distance metrics. Our frame analysis shows that English names more often emphasize Location and Specialty, while Chinese names more often emphasize Positivity and Ambiance. Furthermore, we observe that for Chinese restaurants located in urban areas, those in counties with a higher concentration of Chinese population, or those that are relatively new, the discrepancies between the English and Chinese names are noticeably larger. Finally, interviews with 10 Chinese restaurant owners reveal additional interesting insights regarding naming conventions.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35190

LEAP: a Latent Embedding Anomaly Patch-Transformer for time-series anomaly detection

Cristhian Moya-Mota, Ignacio Aguilera-Martos, Diego García-Gil, Julián Luengo

原文摘要

Time-series anomaly detection is dominated by reconstruction-based neural detectors, whose objective is structurally flawed. Since the target is also the input, an expressive model can learn to reconstruct anomalies too, leaving uninformative residuals. Recent large-scale benchmarks show that, on curated data, elaborate deep detectors rarely beat simple statistical baselines, while current leaders rely on representation learning. We propose LEAP (Latent Embedding Anomaly Patch-Transformer), which combines masked prediction with latent representation-based anomaly evidence, without relying on reconstruction or attention-based scoring. The model removes patches from a window and predicts them from the remaining temporal and cross-channel context, so prediction errors measure how well learned dynamics explain hidden segments. Deterministic complementary group masking ensures every time step is scored while hidden, with identical visible fractions during training and inference. LEAP adds three label-free evidence sources: latent-embedding novelty calibrated by local density, local temporal contrast, and per-channel novelty pooled over channels selected by six label-free criteria. Under the TSB-AD protocol, the full model achieves a VUS-PR of $0.5179 \pm 0.0022$ on $180$ held-out multivariate series. On TSB-AD-U, a univariate variant combining multi-scale masked-prediction scoring with latent novelty, without contrast or channel-pool novelty, achieves $0.6194 \pm 0.0016$ on $350$ held-out series. Both results average three random seeds. A five-stage ablation on TSB-AD-M, supported by paired Wilcoxon signed-rank tests, shows statistically significant gains from each successive component.

cs.LG

查看论文
arXiv ↗PDF ↗