跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+979新增论文
+781其中 AI 相关
+119已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 01:56 — 2026-11-21 01:56(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:2026-11-20 08:48最近发现新增版本:2026-11-20 19:58库内论文最新更新时间:2026-11-20 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。

28,961 已收录论文24,030 AI 相关8,912 有修订112 HF 社区发现

浏览论文库

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 21,358 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.22136

Big Brains, Tiny Board: Pupavision, an Agentic Physical AI Instrument for Monitoring Drosophila Pupariation and Lifecycle Transitions

Joel Sadler, Daniel Graham, Melanie Worley

原文摘要

Many biology experiments are limited by the availability and ease of use of instruments that monitor and record them. For example, the timing of pupariation in the fruit fly Drosophila melanogaster, a widely used model organism, can provide biologically relevant information about growth regulation and is often recorded manually. Here, we present Pupavision, a small physical AI instrument built from a single-board Linux computer and a day/night camera for roughly 45 to 75 US dollars in parts. The key idea is that a frontier coding agent runs its agentic harness directly on the tiny board. The model thinks in the cloud, but the agent works on the device. The agent assists image capture, writes code to repair errors, and checks the experiment every day to keep raw data capture reliable. If recording stops, the researcher gets a ping on their mobile phone. A simple deterministic capture service records one image every ten minutes and never depends on the agent. We report a 26-day pilot in a fly incubator (about 3,580 frames), including eleven days in which the agent was logged out and capture continued, and a 51-hour outage whose cause led to the layered design. A researcher-in-the-loop workflow then produces per-vial pupariation curves by tracing selected pupae backward in time from a late reference frame. Future work will validate the assay for lifecycle tracking accuracy against expert-labeled data and expand real-time computer vision analysis. Pupavision offers a blueprint for do-it-yourself agentic instruments that put frontier intelligence on a tiny board, with deterministic code underneath. We present this as an early case study from a pilot lab deployment and contribute lessons learned toward a future where scientific domain experts are empowered by DIY agentic hardware.

cs.AI · cs.HC

新论文 · v1arXiv:2611.22133

ReMoE: An Interpretable Mixture-of-Experts Framework for Human Mobility Recovery Forecasting Across Disasters

Yilin Lyu, Kang Liu, Wei Wang, Qifan Zhang, Ling Yin, Yushi Bai

原文摘要

Human mobility often declines sharply following disasters and subsequently exhibits complex recovery dynamics. Effective forecasting of this recovery is critical for timely assessment and resource allocation. However, existing approaches are often developed for individual events and operate as black boxes, limiting their transferability and interpretability beyond the events they were trained on. Recent studies have identified recurring post-disaster mobility recovery types across disasters, suggesting that recovery knowledge may be transferable. Motivated by this, we propose ReMoE, an interpretable mixture-of-experts framework for cross-disaster mobility recovery forecasting. ReMoE uses a feature-guided router to adaptively combine specialized experts that learn these heterogeneous yet reusable recovery types, producing a region-specific recovery pattern. It further refines this pattern through residual correction informed by forecasts of future hazard conditions. We evaluate ReMoE on a large-scale mobility dataset covering 18 disaster events spanning hurricanes, floods, winter storms, and wildfires. ReMoE is competitive in-distribution and achieves the strongest performance on unseen events and hazard types, with larger gains under greater distribution shifts. Further analyses show that ReMoE yields interpretable learning outcomes and maintains robust performance under uncertainty. Broadly, ReMoE offers a transferable and traceable forecaster that can support anticipatory post-disaster assessment.

cs.LG · cs.CY

版本更新 · v2arXiv:2611.18467

Score-based neural ordinary differential equations for reaction-diffusions

Jianguo Hou, Wuchen Li

原文摘要

A diffusion equation can be rewritten as a transport equation driven by the score function of the evolving density. Conventional probability-flow formulations, which move particles deterministically with this score-driven velocity, typically conserve total mass. In this work, we develop a Lagrangian method for reaction-diffusion equations in which each particle carries a position and a physical weight. The characteristic ODEs incorporate source terms into the evolution of the log-density and its gradient, while particle weights track changes in mass. We combine this representation with a learned velocity field and weighted particle training to approximate these dynamics. For non-increasing reaction rates, a relative-entropy inequality supports the mass-normalized self-consistency residual as the training objective. This objective can control the error of the induced density when the growth rate is bounded. The algorithm divides the time interval into short windows. In each window, a frozen velocity generates the particle data for a regression of the network velocity. We draw the particles from period-adapted initial sampling distributions and weight them in the loss partly by their predicted future mass, because the reaction can make regions with little initial mass important later. We numerically investigate the method on the Ornstein-Uhlenbeck (OU) equation with a linear source term, Fisher-KPP equations, and Wasserstein-Fisher-Rao gradient flows.

math.NA · cs.LG

新论文 · v1arXiv:2611.22130

Bandit Online Submodular Minimisation Using Zeroth-Order Oracles

Amir Ali Farzin, Philipp Braun, Iman Shames

原文摘要

We consider online submodular minimisation under bandit feedback, where at each round a decision maker plays a subset and observes only its cost, while the cost functions, and hence their minimiser, change over time. Existing bandit methods only guarantee static regret, which compares against a single fixed subset and is a weak benchmark when the minimiser moves. This paper provides, to the best of our knowledge, the first method with guarantees for tracking a moving minimiser in this setting. We propose a zeroth-order method built on a two-point oracle for the Lovász extension whose two evaluations are both subsets that can be played. The perturbed and base points are rounded by a common random threshold, and drawing the smoothing direction from the unit sphere makes the base evaluation a zero-mean control variate, so the oracle is an unbiased estimator of the smoothed gradient. We establish dynamic regret bounds of order $O\big((1+\sqrt{P^\ast_N})N^{3/4}\big)$ in general and $O\big((1+\sqrt{P^\ast_N})N^{2/3}\big)$ under a sufficiently small drift, where $P^\ast_N$ is the path length of the minimiser sequence, together with the corresponding $O(N^{3/4})$ and $O(N^{2/3})$ static regret bounds. Numerically, the method attains lower regret than the algorithm of (Hazan and Kale (2012)), with the advantage growing with the path length.

stat.ML · cs.LG

新论文 · v1arXiv:2611.22128

TempQuant: Learning Adaptive Temperatures for Quantized Language Models

Mukund Athmaram, Liang Ma, Manoj Rao

原文摘要

Large language models are increasingly deployed at low precision, yet quantization can degrade their performance. We study how quantization interacts with decoding settings such as the sampling temperature and top-p by examining how it distorts the model's next-token probabilities. Measuring entropy during generation across deployed temperatures, we find that quantization warms the model on average, and that temperature matters much more for the performance of a quantized model than for its full-precision counterpart. Because quantization and temperature both shape the next-token distribution, we investigate how much the sampling settings can undo what quantization changes, through our method TempQuant, which learns the quantized model's temperature and top-p to bring its next-token probabilities closer to the full-precision model's. We learn these settings at two granularities. The first is a single global setting per requested temperature, which finds nearly the same temperatures that tuning on labeled answers would, without any labels. Model cards typically recommend sampling a quantized model with the same settings as its full-precision counterpart, while we find that different settings can substantially improve its accuracy. On 3-bit Qwen3-4B, for example, global TempQuant raises MATH accuracy from 34% under the configuration recommended for Qwen's quantized releases to 51%. The second sets the temperature and top-p for every token, motivated by our finding that tokens whose rankings flip under quantization tend to need warming, while tokens whose rankings are preserved tend to need cooling. When quantization degrades accuracy substantially, TempQuant recovers much of it, and when degradation is lighter, it still brings the quantized model's behavior closer to the full-precision model's.

cs.LG

版本更新 · v2arXiv:2611.04331

Warpline: Binary-Level Tracing and Unified Evidence for Agentic GPU Kernel Optimization

Junyu Yin, Vinod Grover, Keren Zhou

原文摘要

LLM agents are becoming GPU kernel engineers, but they still tune kernels without seeing where the time goes. Hardware profilers report how busy each unit was, not where each warp's time went; intra-kernel tracers can show it, but only with hand-placed probes and a recompilation that alters the very kernel being measured. We present Warpline, which gives agents this view automatically while leaving the kernel essentially unchanged. Warpline analyzes the binary to decide which events to record and inserts probes into the binary itself without recompilation or any manual step. It then aligns the trace with hardware profiling data on one unified timeline. Because it needs only the binary, it can regenerate this evidence for every new version of the kernel at whatever level the agent edits it (source, IR, or PTX), closing the optimization loop without human intervention. On NVIDIA B200, across 35 kernels in Triton, CuTe DSL, and CUDA C++, Warpline adds a median overhead of 1.2% and leaves a median 99.9% of executed instructions unchanged, whereas existing tracers have median overheads of 1.6% to 13.2% and leave only 4.6% to 32.7% unchanged. Warpline also traces closed-source kernels, which these tracers cannot. On 10 SOL-ExecBench problems, agents using Warpline spend less time and fewer model requests than a bare coding agent and NVIDIA's Kernel Design Agents (KDA), yet lead both after every round in geometric mean and reach a 7.69$\times$ geometric-mean speedup, against 6.94$\times$ and 6.13$\times$. Two case studies further demonstrate that Warpline reveals hidden bottlenecks and provides actionable optimization insights.

cs.PF · cs.PL

新论文 · v1arXiv:2611.22124

FrameSeg3D: Learned Local Frames for Segmenting Small Parts on High-Resolution 3D Scans

Xinwen Zhang, Tongyan Wang, Huawei Lin

原文摘要

Segmenting small parts on high-resolution 3D scans, such as nails on hand scans and teeth on intraoral scans, poses three challenges: 1) each part covers a tiny fraction of the scan, 2) its boundary is only a subtle change of height and curvature, and 3) it faces its own direction. Existing methods fall into two groups, and both fall short. The first group processes the whole scan at once and sees each part too coarsely. Point and mesh networks must shrink the scan to fit in memory, so a small part keeps only a few of its points. Multi-view methods render images of the whole object, so each part fills only a few pixels and a tilted part is seen from the side. The second group first finds each part and then segments it up close. But these methods find the parts with knowledge about one kind of part, for example the shape of the dental arch for teeth. Such knowledge does not carry over to other kinds of parts. We find that accuracy is limited by how a part is seen, from which direction and at what scale, not by how many points land on it. We therefore present FrameSeg3D. It first predicts a local frame for every part, its center and the direction it faces, from a low-resolution view of the whole scan. It then segments the part in views around its frame normal at the scanner's resolution, so covering the whole scan no longer costs resolution. Because every part arrives centered, facing the camera, and at a fixed scale, one segmentation network can serve different kinds of parts and learn from few labeled masks. We test FrameSeg3D on two kinds of parts, nails and teeth. It outperforms state-of-the-art methods on hand scans (mean Dice 0.970 on nails) and on the Teeth3DS+ test fold (per-tooth IoU 96.5), with the most accurate tooth boundaries (boundary IoU 70.5).

cs.CV · cs.GR

新论文 · v1arXiv:2611.22122

Low-speed Limit Cycle Walking of Planar X-shaped Bipedal Robot with Special Properties

Fumihiko Asano, Cong Yan

原文摘要

This paper proposes a novel planar semicircular-footed X-shaped bipedal robot in which the center of mass of each leg link is at the same position as the hip joint, and discusses a method for generating a stable limit cycle gait on level ground. First, we outline the assumptions of the robot model with four degrees of freedom, and develop the mathematical equations of motion and collision. Second, we set the relative hip-joint angle as a control output and design a control system to follow it to the desired trajectory specified as a fifth-order function of time. Third, we mathematically show that there are special properties: the angular velocity of the swing leg does not change before and after the collision, and the time-integral of the control input becomes zero in a steady gait. We also mathematically show that the model has the feature that approximate linearization is effective and the antigravity effect of semicircular feet can be utilized. Through numerical simulations, we verify the validity of the theoretical results, and analyze some fundamental gait properties such as convergence speed and mechanical energy restoration.

cs.RO

版本更新 · v3arXiv:2507.14760

QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems

Cassandra Tong Ye, Shamus Li, Tyler King, Kristina Monakhova

原文摘要

While deep learning offers tremendous promise for scientific and medical imaging, any failures and hallucinations (predictions that do not coincide with reality) are hard to pinpoint and can have serious downstream consequences. Uncertainty estimation techniques, such as conformal prediction, can help by predicting statistically valid error bars for a model's prediction. However, popular conformal prediction methods were not designed for high-dimensional image-valued problems and do not take into account spatial correlations within an image during conformal calibration, resulting in larger-than-necessary uncertainty intervals. We propose a practical simultaneous quantile regression method that enables non-linear, spatially-adaptive scaling during conformal calibration. Our method, QUTCC uses a U-Net architecture with a quantile embedding to learn a full conditional quantile distribution during training, and then leverages this non-linear, learned function for spatially-adaptive conformal calibration. At test time, our method can efficiently estimate uncertainty intervals with pixel-marginal coverage guarantees. In addition, QUTCC can also predict pixel-wise conditional probability density estimates without any built-in distributional assumptions. We evaluate our method on several denoising problems, accelerated magnetic resonance imaging, and quantitative phase microscopy. Our method consistently produces tighter uncertainty intervals than prior conformal methods at the same coverage level, can predict plausible conditional distributions for different tasks, and in some cases, high-uncertainty regions can help us locate hallucinations in a model's prediction.

eess.IV · cs.AI · cs.CV · cs.LG

新论文 · v1arXiv:2611.22117

RetiDual-Select: Reliability-Aware Specialist-Generalist Routing for Retinal OCT under Image-Quality Shift

Zihao Han, Philippe De Wilde

原文摘要

Adaptive fusion can repair a static ensemble's errors, but can also overturn correct decisions. RetiDual-Select combines retinal specialist RETFound with the image encoder of the medical vision-language model MedSigLIP, separating candidate fusion, routing safety and predictive review. Calibrated product-of-experts (PoE) fusion is the static reference, a small gate proposes an alternative for each image, a validation-frozen harm guard decides whether that candidate may replace the reference, and a separate score prioritizes review. Static PoE reached the highest or joint-highest clean accuracy on all three datasets. At a clean 2% accepted-error target the review policy accepted 94.3% of Kermany-4 images at 99.89% selective accuracy, and 92.4% of OCT-C8 at 98.65%. Both branches were correct on 95.0% and 91.8% of clean images; only 4.4% and 6.2% had exactly one correct branch. Across 15 prespecified synthetic conditions, adaptive gains were concentrated in severe contrast reduction, where this routing opportunity widened roughly ninefold; percentile rescaling largely removed the effect, linking it to compressed dynamic range. In post-hoc validation-only analyses, gain was higher when the gate followed the more reliable branch, and a frozen guard cut the worst-condition OCT-C8 loss from 1.39 to 0.36 percentage points. Adaptive routing was useful when image quality created a reliability opportunity and the gate followed it; otherwise the system retained Static PoE or deferred for review. The findings are bounded by the synthetic perturbations evaluated and do not establish robustness to natural acquisition or scanner shift.

cs.CV

新论文 · v1arXiv:2611.22115

TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks

Xingchen AGI Lab, :, Baotian Hu, Bingkai Yang, Boyang Wang, Changzai Pan, Chao Lyu, Chao Wang 等 140 位作者

原文摘要

We present Xing 4, a series of large language models that extends the TeleChat lineage through coordinated advances in model architecture and training infrastructure on Ascend. This report describes the design principles and systems engineering behind the series, spanning architecture selection, large-scale pretraining, and reasoning and agentic post-training. We study how sparse activation, attention design, model depth and width, and speculative decoding balance model capacity with computation, memory access, and execution overhead. Our pretraining infrastructure builds on MindSpore HyperParallel, combining topology-aware hybrid sharding, efficient distributed optimizer execution, and coordinated management of long-sequence workloads and activation memory. CPU affinity and core isolation further reduce host scheduling interference. Together, these mechanisms support the pretraining of a 285B-parameter model on 8,192 Ascend 910C cards, providing a concrete setting for the architectural and systems studies. For post-training, we introduce TeleGym, a unified agent execution platform that connects execution, evaluation, and trajectory construction to policy optimization. Disaggregated asynchronous execution, bounded oversampling, and partial rollout accommodate heterogeneous task durations while preserving trajectory continuity across policy updates. Together, these advances establish an Ascend-oriented training foundation for the continued development of Xing 4 across model scales and increasingly demanding reasoning and agent workloads.

cs.AI

新论文 · v1arXiv:2611.22113

RegimeCouncil: Paired-Evidence Routing For Memory Conflict Governance In LLM Agents

Qingcan Kang, Mingyang Liu, Shixiong Kai, Tao Zhong, Mingxuan Yuan

原文摘要

Language agents rely on long-term memory to personalize responses across extended interactions, yet stored facts quietly go stale as the world changes, and an agent often learns that using memory hurt only through delayed feedback after acting on an outdated record. Before the memory store is updated, how far should that negative feedback propagate: should it suppress memory use only on future queries for that same fact (a local policy), or also across other stored facts (a global policy)? Existing memory systems implicitly fix one of these two sharing scopes at design time. We formulate this online scope choice under hidden validity and delayed feedback as memory conflict governance, and prove that neither fixed policy is sufficient on its own. We then propose RegimeCouncil, a lightweight paired-evidence router that retains both scopes as advisors and arbitrates between them online without retraining the LLM. Using revealed comparisons between answering with memory and answering without memory (the no-memory anchor), a Local Advisor tracks the latest outcome on the queried fact alone, while a Global Advisor pools recent outcomes across all stored facts. A Meta Governor follows the Local Advisor by default to avoid cross-fact interference and switches to the Global Advisor only when global pooling accumulates a strictly positive recent utility margin, guaranteeing finite-time switching under delayed feedback. Across LongMemEval update streams and real-world historical drift on TempLAMA and TAQA with Qwen3-30B-A3B and GPT-4o, RegimeCouncil outperforms the better fixed-scope policy by 5.2-7.3 points on primary disagreement episodes and across all 30 held-out settings, while ablations show that removing any of its three modules reduces accuracy by 2-7 points.

cs.AI

版本更新 · v5arXiv:2610.21337

Does On-Policy Distillation Need to Complete Every Rollout?

Zhengxin Zhang, Maosen Tang, Ning Wang, Changhao Li, Jingren Zhou, Bo Dai, Sainyam Galhotra, Alex Townsend 等 9 位作者

原文摘要

On-policy distillation (OPD) transfers teacher knowledge to a student through feedback on student-generated rollouts, but generating complete rollouts and computing per-token teacher feedback are computationally expensive. Existing truncation methods save computation by stopping rollouts early. However, they do not compensate for truncated token gradients, which biases the gradient estimates and changes Vanilla OPD's original training objective. Furthermore, their truncation decisions rely on assumptions about supervision quality or criteria that may not generalize across settings. We introduce Stochastic Truncated On-Policy Distillation (STOPD), which accelerates OPD by randomly truncating student rollouts and correcting the resulting sampling bias with blockwise inverse-probability weighting (IPW). At each training step, we sample a stopping position for each rollout before generation and let the student generate until that position or natural termination. We obtain teacher feedback on every generated token and use blockwise IPW to compensate for the lower probability of retaining later tokens while controlling the weights. We prove that this weighting preserves Vanilla OPD's gradient sum in expectation and derive one-step update-error bounds for SGD, Adam, and Muon. We evaluate STOPD across multiple teacher-student model pairs, task domains, and optimizers. STOPD reduces generated tokens by 25-48% while maintaining accuracy comparable to Vanilla OPD, achieving 1.3-2.2x training speedups.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.14434

Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL

Jianbo Zhu, Xing Fang, Jing Wang, Mingmin Jin, Bokang Wang, Guangxin Song, Zhenyu Xie, Junjie Bai

原文摘要

Generative retrieval offers a promising alternative by unifying the fragmented multi-stage retrieval process into a single end-to-end model. However, its practical adoption in industrial e-commerce search remains challenging, given the massive and dynamic product catalogs, strict latency requirements, and the need to align retrieval with downstream ranking goals. In this work, we propose a retrieval framework tailored for real-world recall scenarios, positioning generative retrieval as a recall-stage supplement rather than an end-to-end replacement. Our method, CQ-SID (Category-and-Query constrained Semantic ID), employs category-aware and query-item contrastive learning along with Residual Quantized VAEs to encode items into hierarchical semantic cluster identifiers, significantly reducing beam search complexity. Additionally, we develop EG-GRPO (Expert-Guided Group Relative Policy Optimization), a reinforcement learning approach that aligns generative recall with downstream ranking under sparse rewards by injecting ground-truth samples to stabilize training. Offline experiments on TmallAPP search logs show that CQ-SID achieves up to 26.76% and 11.11% relative gains in semantic and personalized click hitrate over RQ-VAE baselines, while halving beam search size. EG-GRPO further improves multi-objective performance. Online A/B tests confirm gains in GMV (+1.15%) and UCTCVR (+0.40%). The generative recall channel now contributes substantially in production, accounting for over 50.25% of exposures, 58.96% of clicks, and 72.63% of purchases, demonstrating a viable path for deploying generative retrieval in real-world e-commerce systems.

cs.IR · cs.AI

新论文 · v1arXiv:2611.22109

VTT: Reading Vehicle Size and Powertrain Type from Motion Trajectory Across Unseen Car Models

Yuhang Wang, Yuechen Guo, Jingxin Yang, Chuheng Wei, Suyang Chen, Abdulaziz Alhuraish, Yiyi Wang, Mingyang Ban 等 10 位作者

原文摘要

Vehicle size and powertrain information can enrich trajectory data for traffic analysis and simulation. We present VTT, a dataset and benchmark for identifying these attributes from motion and controller area network (CAN) signals across unseen car models. The dataset contains 9,062 drives, about 3,950 h, from 1,431 vehicles and 174 car models. It provides three footprint-based size classes, powertrain labels, and evaluation on unseen car models and unseen drivers. Using 60-s windows, we compare four sequence architectures, statistical features and physical features proposed by large language models. Training with auxiliary physical targets, data augmentation and task-specific weighting raises drive-level macro-F1 to 92.6-93.0% for battery-electric versus combustion vehicles and from 62.9% to 67.1% for size classification. On public logs from 4,061 additional drivers, the full-input model identifies powertrain correctly for 86 of 88 car models; size accuracy is 63.2%, close to the internal vehicle-level result of 63.5%. Physical-feature analysis links powertrain recognition to deceleration behaviour and size recognition to steering response. Errors near size-class boundaries and limited gains from longer observations highlight the importance of label resolution and training-fleet coverage for cross-model generalisation.

cs.LG · cs.RO

新论文 · v1arXiv:2611.22103

From Sorry to QED: Refining LLM Math Proofs via Angelic Execution

Yanju Chen, Hanzhi Liu, Ruizhe Qian, Jiaming Shan, Xu Yang, Yufei Ding, Osbert Bastani, Yu Feng

原文摘要

Large language models (LLMs) can now generate Lean proof scripts that capture the high-level structure of many mathematical arguments. However, these scripts frequently fail on complex theorems: a single missing side condition or misapplied lemma can cause the prover to abort early and discard an otherwise viable proof outline. This paper presents MathEye, a framework that converts imperfect LLM-generated proof scripts into fully verified Lean proofs by combining symbolic reasoning with minimal human interaction. At the core of MathEye is angelic proof checking, an optimistic execution model that replaces failing proof fragments with placeholders while preserving the overall structure of the argument. This optimistic check produces an angelic proof that isolates the exact proof obligations that the LLM fails to discharge. Because these unresolved obligations are often logically interdependent, asking a mathematician to address every placeholder directly is inefficient. To minimize human effort, MathEye performs residual analysis over a proof dependence graph that captures symbol-level data flow in the angelic proof. By formulating obligation selection as a MaxSAT optimization problem, MathEye selects a minimal-cost set of essential obligations whose resolution suffices to complete the entire proof. MathEye presents these essential obligations to the mathematician in ordinary mathematical language and uses the mathematician's answers to automatically reconstruct the complete Lean proof. Experiments on 30 real-world benchmarks across analysis and algebra show that MathEye solves 93.3% of the problems while reducing the number of required user interactions by 55%.

cs.AI

版本更新 · v2arXiv:2610.02975

Reliable Self-Evolution with Imperfect Proxy Rewards

Kangjun Noh, Soyu Kim, Kyungwoo Song

原文摘要

Large language model (LLM)-based self-evolving search is a promising approach to scientific discovery. However, high-fidelity evaluation of every candidate is prohibitively expensive in some domains. Self-evolving systems in such settings therefore rely on low-cost but imperfect proxy rewards, which may assign high scores to infeasible candidates. These false positives may contaminate both the final output and the feedback used to guide subsequent generations. This motivates statistically calibrated reward intervals for more reliable self-evolving search. We propose Conformal Interval-Driven Self-Evolution (CISE), which constructs candidate-specific reward intervals using conditional conformal inference and iteration-wise online density-ratio estimation. CISE uses conservative interval-based rewards for evolutionary feedback and returns candidates only when all required property intervals lie entirely within their respective feasible regions. We derive fixed-iteration coverage results under explicit assumptions of independence and covariate shift. We evaluate CISE on three self-evolving search tasks in materials science. In our experiments, all candidates returned by CISE are true positives under high-fidelity evaluation, whereas the baselines return more candidates but include false positives. These results highlight the value of a smaller, more precise shortlist when downstream validation budgets are limited. Our repository is available at https://github.com/MLAI-Yonsei/CISE.git.

cs.AI

版本更新 · v2arXiv:2611.10397

Regularization Amplifies Subliminal Learning

Lawrence Feng, Jacob Mitchell Springer, Gaurav R. Ghosal, Ziqian Zhong, Aditi Raghunathan

原文摘要

Recent work has shown that hidden biases can be transferred through data with no apparent semantic relationship to those biases. Can regularization limit this covert influence? By constraining adaptation, regularization might be expected to suppress behavioral changes on seemingly unrelated inputs. We systematically study this hypothesis in subliminal learning, as well as in related settings of covert influence, including phantom transfer and logit-linear selection. We find the opposite: regularization amplifies the transfer of hidden biases. In particular, subliminal learning is typically absent under full fine-tuning, but low-rank adaptation or explicit penalties can induce strong transfer. Phantom transfer and logit-linear selection show similar trends. Adding more data, an implicit form of regularization, also strengthens covert influence. Together, these findings suggest that the simplicity biases induced by regularization may facilitate covert influence. We further hypothesize that the level of regularization that maximizes covert transfer depends on task complexity.

cs.LG

新论文 · v1arXiv:2611.22102

EvoDisco: Strategy Discovery for Evolving Agent Memory

Mingyang Liu, Qingcan Kang, Shixiong Kai, Kaichao Liang, Xiaojin Fu, Tao Zhong, Linqi Song

原文摘要

Large language model agents accumulate experience in memory, and how that memory evolves during interaction is as important as what it stores. Recent methods update memory online, yet both the operators that transform memory and the rules that select them remain fixed by design. We propose EvoDisco, which formulates agent memory evolution as evolutionary strategy discovery: the agent must discover which operator to apply, when to apply it, and how to instantiate it, rather than rewriting memory under a static operator schedule. A learnable policy conditions on the current memory state and recent task history, then selects and instantiates one of four semantic operators---Abstract, Refine, Bridge, and Reframe---which respectively compress related memories, decompose overloaded entries, connect weakly linked experiences, and reorganize retrieved reasoning chains. The policy is updated with a bi-level fitness. An inner signal scores each transformation using a retrieval-quality improvement regularized by memory complexity. An outer signal scores strategic efficacy over a window of past decisions, combining historical operator-utility regret, utility-prediction error, and selection diversity. Under a one-pass online plus frozen-transfer protocol on ALFWorld, WebShop, and LifelongAgentBench (OS and DB), EvoDisco improves over strong memory baselines including MemP and MemRL. The largest gains are on ALFWorld ($+8.8$ online / $+12.9$ frozen-transfer points over MemP; $+16.4$ / $+17.9$ over MemRL). Ablations attribute these gains to both fitness levels and the operator library.

cs.AI

新论文 · v1arXiv:2611.22101

An Omnidirectional WECT: Closed-Form Computation of the Directionally Integrated Weighted Euler Characteristic Transform

Jessi Cisewski-Kehe, Brittany Terese Fasy, Alexander McCleary, Eli Quist, Jack Ruder, Jacob Sriraman

原文摘要

The weighted Euler characteristic transform (WECT) and related directional descriptors have become popular, efficiently computable tools for shape analysis across a variety of domains. In practice, however, they are approximated over a finite set of filtration directions, and thus the vectorized descriptor depends on this choice of directions and the rotational orientation of the data. In this manuscript, we formally introduce the directionally integrated weighted Euler characteristic transform (DIWECT), which averages the WECT over all directions $s \in \mathbb{S}^n$ for a weighted simplicial complex immersed in $\mathbb{R}^{n+1}$. A framework for computing the DIWECT exactly, without sampling directions, is outlined: for each simplex, we partition $\mathbb{S}^n$ into the sets of directions in which a given vertex enters the filtration last, and then the DIWECT at height $t$ reduces to measuring intersections of these regions with a set of directions in which the simplex has entered the filtration by height~$t$. We provide implementations for complexes immersed in $\mathbb{R}^2$ and $\mathbb{R}^3$, in which case the problem reduces to computing arc lengths and spherical areas. Experiments on synthetic and real-world data show that the DIWECT, while resulting in more compact vectorizations, also successfully encodes shape information and discards noise from data orientation. On a barley seed classification task, it outperforms the WECT in every pose except a hand-curated frame, whose advantage disappears under a two-degree rotation error. Compared with averaging the WECT over sampled directions, the DIWECT is often faster at matched accuracy. In one instance, this is upwards of a $50 \times$ speedup on a one-million-cell image with an error of $10^{-3}$.

cs.CG

新论文 · v1arXiv:2611.22100

Semantic Communication via Analog RF Computing: When the Radio Computes the Meaning

Christo Kurisummoottil Thomas

原文摘要

Semantic communication (SC) systems transmit continuous latent representations of meaning, but computing the semantic encoder at resource-constrained edge devices incurs substantial energy and memory costs. To address this challenge, we propose an end-to-end SC framework that executes the semantic encoder in the client's RF receiver front end using analog RF computing. A base station (BS) broadcasts encoder weights as RF waveforms, while each edge device reuses its receiver's passive mixer to compute semantic latents at ultra-low energy. These latents are transmitted over the uplink for network-side task inference. We show that analog computing noise across encoder layers and channel noise affecting transmitted latents admit a unified mathematical model. We define a task-posterior semantic distortion metric and derive its second-order decomposition into per-client, per-stage semantic sensitivities. Using this decomposition, we obtain a closed-form semantic-aware water-filling allocation of the total client energy budget across clients, encoder layers, and uplinks, assigning tighter accuracy targets to semantically sensitive stages. This allocation induces a broadcast beamforming problem that accounts for client-specific, per-layer accuracy requirements. We further refine the allocation through stochastic optimization and jointly design it with multi-task noise-aware training of the shared semantic model. MNIST simulations show that, at matched total client energy, the proposed allocation reduces network semantic distortion by 9.2\%-19.2\% compared with uniform precision and 5.1\%-13.1\% compared with client-blind allocation. Noise-aware co-design yields a further 46\% reduction.

eess.SP · cs.AI · cs.IT

新论文 · v1arXiv:2611.22099

Differentiable High-Order Mesh $r$-Adaptivity

Ketan Mittal, Julian Andrej, John Camier, Veselin Dobrev, Tzanio Kolev, Leonardo Molinari, Vladimir Tomov

原文摘要

High-order mesh r-adaptivity typically entails minimizing a nonlinear functional using its gradients and, for Newton-based methods, its Hessian. These derivatives can be expensive to derive, must be updated with any changes to the functional, and errors in the derivatives directly impact the convergence of r-adaptivity. Additionally, derivatives of the r-adaptivity operator are required for consistent sensitivity analysis for inverse problems. This work develops a framework for differentiable r-adaptivity based on the Target-Matrix Optimization Paradigm. Given a pointwise functional defining the local mesh-adaptation objective, the proposed framework uses $\partial$FEM to automatically generate pointwise first- and second-order derivatives. These local derivatives are then assembled into a global gradient vector and a Hessian operator through the finite element operator decomposition. The derivative kernels support portable CPU and GPU execution, with partial assembly and tensor sum factorization enabling matrix-free application of the Hessian operator. The framework also provides consistent sensitivities of the r-adaptivity operator through automatically generated mixed derivatives and implicit differentiation of the mesh stationarity equations. Numerical experiments show GPU solve times comparable to those of hand-derived TMOP implementations on a benchmark problem, improvement in r-adaptivity convergence due to accurate computation of the derivatives, and demonstrate the use of mesh sensitivities for material-interface identification in an inverse heat-conduction problem.

math.NA · cs.MS

新论文 · v1arXiv:2611.23336

RootSink: Reproducible C/C++ Crashes with Tested Repair Sites

Suryansh Singh Sijwali, Achintya Lakshmanan, Abhiram Dodda, Shaiful Chowdhury, Suman Saha

原文摘要

When a C or C++ program crashes on a crafted input, the line that crashes is often not the line that is wrong. Tools and models that repair or locate vulnerabilities need examples showing both, with evidence for each, which existing datasets rarely provide. RootSink provides 3341 records from 354 open-source projects. Most give the crash site a memory-error detector reported and a candidate location for its root cause, and label each with a weakness type and its evidence. For the 1954 records in the Reproduced tier, we re-ran the crash ourselves and confirmed that the fixed version runs cleanly. In 1275 of these, a single hunk of the developer's fix stopped the crash on its own. That marks a tested repair site, though not necessarily the defect, and 1273 records use it as the root. In a blind audit of an earlier version, two co-author raters called 68% and 92% of the tested repair sites they saw the defect, but only 37% and 51% of that version's located Reproduced-tier roots. RootSink ships with tasks, a patch scorer and run logs.

cs.SE

版本更新 · v2arXiv:2609.36685

When Semantics Matter: Reliability-Aware Semantic-Rhythm Control for Co-Speech Gesture Generation

Zhirui Xing, Ming Meng, Kaige Li, Ziyi Xu, Zhaoxin Fan

原文摘要

Co-speech gesture generation aims to synthesize natural gestures that are both temporally synchronized with speech and semantically consistent with the spoken content. Although recent methods can generate rhythmically plausible motions, they often rely heavily on acoustic prosody while underutilizing textual semantics, especially when semantic annotations are incomplete, noisy, or unavailable. Consequently, the generated gestures may follow speech rhythm while failing to express the intended semantics. To address this problem, we propose a reliability-aware semantic-rhythm control framework for co-speech gesture generation. We first learn a discrete motion prior that represents continuous gestures in a compact and structured motion-code space. We then introduce a dual-branch semantic contribution estimation mechanism consisting of a full multimodal branch and an audio-only branch. Their distributional discrepancy provides a model-based proxy for text-induced predictive influence, which is interpreted jointly with segment-level semantic relevance. Based on this estimate, a controllable semantic-rhythm objective selectively strengthens semantic guidance in content-relevant segments while limiting unnecessary semantic intervention in rhythm-dominant segments. Furthermore, we treat background noise as an acoustic reliability condition and introduce noise-conditioned feature modulation together with benefit-regularized latent perturbation to improve generation robustness under realistic acoustic environments. Experiments on benchmark datasets demonstrate that the proposed framework achieves a favorable balance among semantic expressiveness, rhythmic synchronization, motion diversity, and robustness, enabling reliable and controllable co-speech gesture generation.

cs.CV

新论文 · v1arXiv:2611.22095

CueSplat: Learning to Schedule Sparse Deformation for Dynamic Gaussian Splatting on Edge Devices

Qingyuan Tang, He Zhu, Shixuan Sun, Anbang Wu, Jingwen Leng, Minyi Guo, Yu Feng

原文摘要

Deformation-based 4D Gaussian splatting (4DGS) enables dynamic scene rendering. However, evaluating deformation networks for all Gaussians at every frame is compute-intensive on edge devices. We find that Gaussian trajectories are often locally predictable, yet prediction reliability varies across Gaussians and time. Thus, we propose CueSplat, a post-training framework that exploits local temporal regularity while keeping the pretrained backbone frozen and retaining its Gaussian set. Specifically, CueSplat predicts Gaussian attributes from recent history and uses a lightweight learned router to select exact deformation updates within a scene-specific budget calibrated offline. Selection accounts for prediction reliability and rendering contribution. Selected indices are reused across nearby frames to reduce routing overhead, while selected Gaussians still receive exact updates each frame. To control accumulated prediction error, we use drift signals to schedule three consecutive full-deformation frames that rebuild the prediction history. Evaluated across four mainstream 4DGS algorithms, CueSplat achieves up to $6.74\times$ and $8.15\times$ speedups on Jetson AGX Orin and Orin NX, respectively, with a negligible quality drop (at most $0.16$ dB in dataset-average PSNR).

cs.CV

新论文 · v1arXiv:2611.22093

Projected Route Cues for Bouldering: Effects of Circular, Linear, and Combined Highlighting on Route Observation and Climbing

Yuki Uranishi, Tamon Hamamoto, Chang Liu, Goshiro Yamamoto, Masato Kobayashi, Photchara Ratsamee, Haruo Takemura

原文摘要

Before attempting a bouldering problem, climbers inspect the route to find its holds and plan their moves, which novices find difficult on walls where many routes overlap. We built a projector-camera system that projects route cues onto the wall and compared three cues: circles on the route holds, limb-colored lines connecting the holds, and both combined. Ninety-six participants, 61 of them first-time climbers, each climbed four routes, one per cue and one without projection, in a Latin-square order. In mixed-effects models, all three cues shortened the time before the first attempt; with circles, its geometric mean fell from 83 s to 39 s. Circles also increased the number of moves made within each trial. Lines led to more use of off-route holds than circles, mainly on routes where such holds lay under the projected lines. Participants preferred the combined cue, although no behavioral advantage of it over circles was detected.

cs.HC

版本更新 · v4arXiv:2602.19202

UniE2F: A Unified Diffusion Framework for Event-to-Frame Reconstruction with Video Foundation Models

Gang Xu, Zhiyu Zhu, Junhui Hou

原文摘要

Event cameras excel at high-speed, low-power, and high-dynamic-range scene perception. However, as they fundamentally record only relative intensity changes rather than absolute intensity, the resulting data streams suffer from a significant loss of spatial information and static texture details. In this paper, we address this limitation by leveraging the generative prior of a pre-trained video diffusion model to reconstruct high-fidelity video frames from sparse event data. Specifically, we first establish a baseline model by directly applying event data as a condition to synthesize videos. Then, based on the physical correlation between the event stream and video frames, we further introduce the event-based inter-frame residual guidance to enhance the accuracy of video frame reconstruction. Furthermore, we extend our method to video frame interpolation and prediction in a zero-shot manner by modulating the reverse diffusion sampling process, thereby creating a unified event-to-frame reconstruction framework. Experimental results on real-world and synthetic datasets demonstrate that our method outperforms previous reconstruction approaches on most quantitative metrics and achieves superior qualitative results, while achieving competitive zero-shot performance compared with dedicated methods explicitly trained for interpolation and prediction tasks. We also refer the reviewers to the video demo contained in the supplementary material for video results. The code will be publicly available at https://github.com/CS-GangXu/UniE2F.

cs.CV

新论文 · v1arXiv:2611.22086

HyCoInfer: Cloud-Edge Collaborative Inference for Large Language Models on Heterogeneous GPU-FPGA Architectures

Zewen Huang, Xiangwen Zhuge, Yingkun Hu, Zheng Yang, Qiang Ma

原文摘要

Large language model (LLM) serving relies predominantly on cloud GPUs, yet autoregressive decoding is memory-bound and often leaves their arithmetic units underutilized. Edge FPGAs offer attractive decoding efficiency, but are ill suited to sustaining a high-concurrency serving workload alone. This paper presents HyCoInfer, a heterogeneous cloud-edge serving system that assigns prefill to cloud GPUs and distributes decoding across cloud GPUs and edge FPGAs. The design addresses three barriers to practical offloading: capacity balancing across heterogeneous accelerators, the large KV cache crossing a constrained wide-area link, and the latency added by heterogeneous execution. HyCoInfer incorporates FPGA decode capacity into GPU prefill/decode role partitioning and places requests according to queue load, prompt length, and network state. It further combines layer-wise pipelined transfer, decoder-side precomputation, and bandwidth-adaptive KV cache compression based on residual vector quantization. We implement HyCoInfer using two NVIDIA V100 GPUs and an AMD Xilinx Alveo U280 and evaluate it over 100-1000 Mbps links. At 500 Mbps, HyCoInfer delivers up to 4.11 times the request goodput of cloud-only vLLM and reduces mean end-to-end latency by up to 61.1%. Across different network conditions and workloads, the system improves overall serving capacity, with the largest gains on communication-intensive tasks, and reduces per-request energy.

cs.OS · cs.AI

新论文 · v1arXiv:2611.22085

ATLAS-Finance: Benchmarking AI Agents in Realistic Banking Environments

Elaine Lau, Antoine Pangas, Alexandre Finot, Collin Schweiker, Amir Bouzidi, Hui Wen Goh, Andrew Peter Martin, Jonas Mueller

原文摘要

Professional work involves under-specified assignments, where relevant information is spread across workplace applications and may conflict or change over time. To evaluate how well frontier agents can perform economically valuable work in such settings, we introduce ATLAS-Finance, a benchmark of 100 end-to-end investment-banking tasks across 13 simulated firms. As in real banking workflows, agents must search email, chat, calendars, notes, and files to identify requirements, gather information, reconcile conflicts/updates, and then build complex financial models. Tasks were developed by experienced bankers based on their real deal work and take them 15-30 hours to complete. Agent deliverables are evaluated with expert-authored rubrics (median: 124.5 criteria) covering financial rationale and results, spreadsheet construction, completeness, and formatting. Despite completing substantial portions of the requested work, current agents rarely produce correct deliverables. Across today's frontier models, the best ones (Claude Opus and Fable) pass fewer than 11% of tasks.

cs.AI

新论文 · v1arXiv:2611.22084

When Lower Harm Misleads: Auditing Concept Corrections

Tianyou Lai, Wentao Yue, Hongji Li, Chaoyuan Hao, Qilei Li

原文摘要

An expert who corrects a concept prediction, such as a BI-RADS descriptor in breast ultrasound, expects the diagnosis to improve. Objectives that reduce the harm of such corrections are judged by harm and accuracy, yet harm also falls when a model responds less to every correction or starts from a worse uncorrected prediction, the reference for harm. We propose a correction audit, a reproducible evaluation protocol that separates these explanations: it splits each correction into harm and useful gain on identical events, separates the starting prediction from the correction response, and compares objectives with amplitude baselines matched in source harm. On three breast-ultrasound sources, worst-case correction training, evaluated from the mean-case model's start, lowers harm but gives up more useful gain in all 21 source comparisons pooled over six seeds, raising the corrected negative log-likelihood (NLL); from the same start, selecting between the objectives by harm picks the less helpful model on all three sources. On CUB, a monotonic harm penalty at its reported weight lowers path-level harm in all 80 concept sets while raising the NLL in all 80, almost entirely before any correction. At a fixed start, rescaling both responses to the same source harm reproduces the penalty's mean harm, useful gain and NLL on single-concept corrections within a prespecified margin of 0.0005 nat, although the two responses point in different directions. Lower harm therefore signals better corrections only when it is read together with useful gain, absolute risk and the start it is measured from.

cs.AI · cs.CV