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

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 21:33 — 2026-11-16 21:33(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:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,921 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 316 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.14196

Joint Quantization and Dynamic Partitioning for Context-Aware Edge Vision Transformers

Zhu Jiaqi, Jain Prakriti, Katare Dewant, Kumar Saurabh

原文摘要

Deploying vision transformer models across connected and automated vehicles (CAVs) requires joint management of computation and Vehicle-to-Vehicle (V2V) communication. Static split-inference methods use fixed partition points and cannot adapt to time-varying link bandwidth, processing load, and concurrent multi-stream traffic. This paper proposes an edge orchestration framework that jointly selects model partition points, per-layer quantization bitwidths, and execution placement across heterogeneous vehicular compute nodes. The joint partitioning and mixed-precision allocation problem is formulated as a Mixed-Integer Linear Program (MILP) that minimizes compute and communication energy subject to end-to-end latency and task-quality constraints. The framework is evaluated on Jetson Orin Nano (8~GB), Jetson Orin NX (16~GB), and Jetson AGX Orin (32~GB) nodes using OPV2V-driven multi-stream workloads with $K \in \{2,4,6,8\}$. Across the evaluated configurations, the proposed formulation reduces V2V communication energy by $33.3$--$36.0\%$ relative to a Uniform INT8 split. At $K=8$, end-to-end task completion latency is reduced by $34.0\%$ on the Orin Nano and $33.1\%$ on the Orin NX relative to the same baseline, while limiting the reduction in 3D detection accuracy to $3.1$--$4.1$ percentage points in $\mathrm{mAP}_{50}$ relative to FP16 execution.

cs.AI

版本更新 · v2arXiv:2602.03623

Self-supervised Physics-Informed Manipulation of Deformable Linear Objects with Non-negligible Dynamics

Youyuan Long, Gokhan Solak, Sara Zeynalpour, Heng Zhang, Arash Ajoudani

原文摘要

We address dynamic manipulation of deformable linear objects by presenting SPiD, a physics-informed self-supervised learning framework that couples an accurate deformable object model with an augmented self-supervised training strategy. On the modeling side, we extend a mass-spring model to more accurately capture object dynamics while remaining lightweight enough for high-throughput rollouts during self-supervised learning. On the learning side, we train a neural controller using a task-oriented cost, enabling end-to-end optimization through interaction with the differentiable object model. In addition, we propose a self-supervised DAgger variant that detects distribution shift during deployment and performs offline self-correction to further enhance robustness without expert supervision. We evaluate our method primarily on the rope stabilization task, where a robot must bring a swinging rope to rest as quickly and smoothly as possible. Extensive experiments in both simulation and the real world demonstrate that the proposed controller achieves fast and smooth rope stabilization, generalizing across unseen initial states, rope lengths, masses, non-uniform mass distributions, and external disturbances. Additionally, we develop an affordable markerless rope perception method and demonstrate that our controller maintains performance with noisy and low-frequency state updates. Furthermore, we demonstrate the generality of the framework by extending it to the rope trajectory tracking task. Overall, SPiD offers a data-efficient, robust, and physically grounded framework for dynamic manipulation of deformable linear objects, featuring strong sim-to-real generalization.

cs.RO

新论文 · v1arXiv:2611.13955

RB-LDC: Redundancy-Balanced Latent Coding for Noise-Robust Diffusion Latents

Hyunseok Jeong, Jaeho Jeon, Young-Sik Kim

原文摘要

Latent diffusion models decode approximately correct latents, making decoder sensitivity to perturbations relevant to image quality. After whitening, forward diffusion corrupts every direction at the same signal-to-noise ratio (SNR), despite unequal decoder sensitivities. We study an invertible linear layer between the encoder and diffusion process that shifts each direction's log-SNR. Its linear minimum mean-square-error (LMMSE) recovery risk has an exact spectral expression for any whitened latent distribution. Under an energy budget and a floor ensuring invertibility, minimizing decoder-sensitivity-weighted LMMSE risk integrated over the diffusion schedule yields a unique optimal allocation. The layer aligns with the decoder's expected pullback metric and equalizes marginal risk reduction across directions, computed by a deterministic spectral solver. At large budgets, the allocation follows a power law in sensitivity whose exponent is determined by the low-SNR tail of the loss weighting: one half for noise prediction and two thirds for data prediction under the cosine schedule, with a crossover on truncated schedules. We instantiate this principle as RB-LDC using Jacobian-based sensitivity estimates. On ImageNet at 256 x 256 resolution with SD-VAE and VA-VAE, trained RB-LDC improves reconstruction from noisy latents over budget-matched isotropic coding in all four metrics and five coding configurations, averaged over 15 SNRs and three pipeline seeds. It reduces average perturbed FID by 17.1 for VA-VAE block-local coding while preserving clean reconstruction. We also report intermediate SNRs where perturbed FID worsens. With a frozen diffusion model, RB-LDC yields lower FID point estimates in all 12 tested combinations of sampling progress and channel SNR under corruption during sampling.

cs.LG · cs.CV

版本更新 · v2arXiv:2611.06625

Dynamic Shape Control of Soft Trunk Robots

Hehui Zheng, Marc Stampanoni, Roshan S. Kaundinya, Ronan Hinchet, George Haller, Robert K. Katzschmann

原文摘要

Controlling the shape profile of soft trunk robots extends their reach into complex regions of the workspace and enhances their use in practical applications. Recent advances in soft robot design have enabled soft trunk robots to achieve greater flexibility in conforming to complex shapes. Specifically, trunk robots whose geometries are designed as helicoids have been shown to enable extreme shape-changing capabilities. Their compliance makes them highly nonlinear, which in turn makes shape control difficult. On similar tendon-driven trunk robots, model-based controllers based on the theory of adiabatic spectral submanifolds (aSSMs) have achieved high accuracy in closed-loop end-effector tracking. We extend this approach by learning an aSSM model of the full body of a trimmed-helicoid soft trunk robot from data and use this in a model predictive control (MPC) scheme to demonstrate a range of shape control tasks on hardware. On closed-loop dynamic shape regulation, our method outperforms the available linear baselines by a factor of 10. In human-in-the-loop interactive demos, our method completes section-by-section shaping and balances a tennis ball for over 25 seconds, while the linear baselines fall short. A model-free reinforcement learning policy trained for 12 hours on hardware fails on the same balancing task. These results establish aSSM-based MPC as a practical route to full-body shape control on real soft hardware.

cs.RO

新论文 · v1arXiv:2611.13938

Dual-Core Tensor Wheel Decomposition with Structure-Cached Acceleration for Tensor Recovery

Wenchao Xie, Qingsong Wang

原文摘要

Tensor wheel decomposition captures complex correlations in high-dimensional data through interactions between outer-ring factors and a high-order central core. However, updating these components requires the explicit construction and manipulation of large-scale matrices, which limits computational efficiency and incurs particularly high computational and memory costs for the central-core update. To address these limitations, we propose dual-core tensor wheel decomposition (DCTW), which factorizes the central core into two lower-order cores linked by a shared latent bond. Each core is coupled to a different group of outer-ring factors. We further propose a structure-cached acceleration strategy that avoids explicit large-scale matrix multi- plications and caches intermediate tensors generated during tensor network contractions for reuse across block updates. This reuse reduces redundant computation and avoids the explicit construction of large matrices. Complexity analysis and experiments show that the strategy based on structural caching accelerates optimization compared with explicit and implicit up- date schemes while limiting the increase in peak memory as the ranks grow. Experiments on color video completion and robust denoising show that DCTW matches or outperforms representative tensor network methods in reconstruction quality, computational efficiency, and scalability.

cs.LG

新论文 · v1arXiv:2611.13757

Stochastic Aggregation with Prescribed Resources and Additive Delay

Tianhang Lu, Runtian Ren, Shengcai Liu

原文摘要

We study online aggregation with prescribed resources and additive delay. In this problem, we are given a finite set of resources with purchase costs and a collection of request types, each specifying the resources it requires. Requests arrive over time, and each request can be served immediately or postponed to a later time. A service may serve several pending requests together by purchasing every resource required by at least one of them, paying for each purchased resource only once. These purchases serve only the current batch; resources needed in a later service must be purchased again. A request served $t$ units of time after its arrival incurs delay cost $t$. The objective is to serve all requests while minimizing the sum of resource purchase costs and individual delay costs. We consider a stochastic version of this problem in which requests of each type follow an independent Poisson process of known rate. An online algorithm knows these rates but observes requests only upon arrival. We compare its expected cost with that of an offline optimum that knows the entire realized input and may choose every batch freely. A resource--scale linear program supplies both an offline lower certificate and synchronized service periods. This yields a deterministic online algorithm with polynomial-time preprocessing on rational input and a long-run ratio of expectations below $2.113$. The guarantee applies in particular to rooted multi-level aggregation and prescribed-pair aggregation on trees. Besides, for Poisson TCP acknowledgment, we further characterize the optimal long-run ratio of expectations at every load, showing that its worst-case value is approximately 1.409 and is attained by a deterministic online policy.

cs.DS

新论文 · v1arXiv:2611.13707

Joint Activation and Weight Quantization for Learned Image Compression

Yile Tu, Heming Sun

原文摘要

Learned image compression (LIC) models achieve competitive rate-distortion performance with increasingly large networks, making network quantization important for efficient deployment. Directly quantizing LIC models remains difficult in post-training quantization (PTQ) because compression performance is highly sensitive to quantization noise. Existing methods typically focus on optimizing either the weights or the activations, resulting in substantial rate-distortion degradation. To address this limitation, we introduce a two-stage pipeline that uses SmoothQuant to balance activation and weight ranges, followed by GPTQ to adapt the transformed weights. The proposed joint search framework optimizes the balancing transformation and adapted weights under the rate-distortion objective, accounting for the coupling between the two stages. Experiments across multiple LIC architectures and activation quantization configurations show that the joint search strategy consistently reduces rate-distortion degradation after quantization.

eess.IV · cs.MM

版本更新 · v2arXiv:2511.22928

Predicting Risks Before They Happen: Vision-Language Reasoning for Autonomous Driving

Jiaxin Liu, Xiangyu Yan, Liang Peng, Lei Yang, Yuechen Luo, Lingjun Zhang, Hangjun Ye, Guang Chen 等 15 位作者

原文摘要

% Waiting until a driving hazard becomes directly visible can leave an autonomous vehicle little time to respond. Observable precursors, such as another vehicle's unexpected braking, can provide evidence of a hidden hazard and an opportunity for earlier risk mitigation. However, existing driving datasets and language reasoning formulations provide limited supervision for connecting these precursors to potential risks and appropriate responses. We introduce PotentialRiskQA, an ego-view driving dataset that marks precursor and risk appearance times and provides structured annotations linking scene evidence, potential risks, and mitigation actions. Building on this dataset, PR-Reasoner trains vision-language models to generate a precursor-centered reasoning chain through scene-level supervision and auxiliary tasks for scene understanding, precursor identification, risk inference, driving suggestions, and meta-actions. Experiments across multiple backbones show improved scene understanding, risk cognition, and action quality, with fewer unsupported risk claims on most models. Ablations show that supervising intermediate reasoning steps further reduces unsupported risk claims and improves action quality beyond scene-level training alone. On NAVSIM, the trained representations improve open-loop planning performance, demonstrating benefits beyond language-based evaluation.

cs.RO

新论文 · v1arXiv:2611.13578

POEM: Output-Relative Block-Sparse Attention for Long-Context Prefilling

Haoyi Wu, Yunkai Dang, Wanyu Zhang, Lei Wang, Wenbin Li

原文摘要

Large language models (LLMs) have shown strong capabilities across diverse applications, making both safety and utility essential for reliable deployment. Jailbreak attacks use diverse forms of adversarial prompting to bypass alignment safeguards and induce LLMs to generate harmful responses. Some representation-based defenses regulate internal activations using predefined steering directions or learned safety regions. However, adapting intervention to each input without a predefined representational target while limiting over-refusal remains a challenge. In this paper, we propose Target-free Entropy-guided Residual Modulation (TERM), an inference-time defense that uses prompt-calibrated attention entropy deviations to guide adaptive modulation of the model's own residual updates. Attention patterns vary across prompts and decoding steps, making raw entropy values difficult to interpret as a consistent signal for intervention. We therefore calibrate attention entropy against each prompt's own prefill baseline to establish an input-specific reference for reducing unnecessary intervention on benign requests. Adaptive scale normalization and temporal accumulation then account for differences in deviation scale and persistence to determine intervention strength. The resulting signal controls bounded scaling of the model's own residual updates, without relying on a predefined safety direction. We compare our method with seven defenses on seven jailbreak attacks and two over-refusal benchmarks across Llama, Qwen, and Gemma models, including Qwen3 models from 0.6B to 32B. Results show our method improves jailbreak robustness while maintaining low over-refusal on benign safety-sensitive requests with modest inference overhead.

cs.CR · cs.CL

新论文 · v1arXiv:2611.13577

TERM: Target-Free Jailbreak Defense via Entropy-Guided Residual Modulation

Yunkai Dang, Wanyu Zhang, Meiyi Zhu, Qi Fan, Tianyu Ding, Wenbin Li

原文摘要

Large language models (LLMs) have shown strong capabilities across diverse applications, making both safety and utility essential for reliable deployment. Jailbreak attacks use diverse forms of adversarial prompting to bypass alignment safeguards and induce LLMs to generate harmful responses. Some representation-based defenses regulate internal activations using predefined steering directions or learned safety regions. However, adapting intervention to each input without a predefined representational target while limiting over-refusal remains a challenge. In this paper, we propose Target-free Entropy-guided Residual Modulation (TERM), an inference-time defense that uses prompt-calibrated attention entropy deviations to guide adaptive modulation of the model's own residual updates. Attention patterns vary across prompts and decoding steps, making raw entropy values difficult to interpret as a consistent signal for intervention. We therefore calibrate attention entropy against each prompt's own prefill baseline to establish an input-specific reference for reducing unnecessary intervention on benign requests. Adaptive scale normalization and temporal accumulation then account for differences in deviation scale and persistence to determine intervention strength. The resulting signal controls bounded scaling of the model's own residual updates, without relying on a predefined safety direction. We compare our method with seven defenses on seven jailbreak attacks and two over-refusal benchmarks across Llama, Qwen, and Gemma models, including Qwen3 models from 0.6B to 32B. Results show our method improves jailbreak robustness while maintaining low over-refusal on benign safety-sensitive requests with modest inference overhead.

cs.CR · cs.CL

版本更新 · v2arXiv:2606.11337

Can AI Agents Synthesize Scientific Conclusions in Health?

Hayoung Jung, Pedro Viana Diniz, José Reinaldo Corrêa Roveda, Abner Fernandes da Silva, Haeun Jung, Enoch Tsai, Aleksandra Korolova, Manoel Horta Ribeiro

原文摘要

Scientific AI agents increasingly retrieve evidence, reason across sources, and synthesize conclusions used in consequential decisions. Yet, their ability to do so in high-stakes domains such as health remains unclear. We introduce SciConBench, a large-scale live benchmark of 9.21K questions and expert-written conclusions from systematic reviews to evaluate open-domain scientific conclusion synthesis in health and medical domains. The benchmark draws on an expert-validated automated evaluation pipeline that decomposes conclusions into atomic facts and measures correctness and comprehensiveness via factual precision and recall. To mitigate data leakage, we further introduce SciConHarness, a clean-room evaluation harness that equips agents with controlled web interaction to ensure valid measurement. Evaluating 8 frontier models and deep research agents, we find that factual quality remains low: under clean-room settings, the best agent achieves only a factual F1 of 0.337. Our clean-room setting consistently reduces performance relative to unconstrained evaluation, suggesting that leakage inflates estimates of models' true synthesis capabilities. Finally, we audit consumer-facing agents (e.g., Google AI Overview, OpenEvidence) and find they frequently generate incomplete and sometimes contradictory conclusions, even when the ground-truth answer is available. Overall, our results show that reliable synthesis of scientific conclusions in health remains an open challenge, and that clean-room evaluation is essential for assessing open-domain AI agents.

cs.AI · cs.CL · cs.CY

新论文 · v1arXiv:2611.13562

An evidence-traceable benchmark of clinical reasoning in large language models

Zhiqun Zhao, Xiaodong Yang, Bruce Gu, Ming Li, Yi Fu, Song Li, Qi Mei, Zhi Liu 等 16 位作者

原文摘要

Benchmark scores for medical large language models (LLMs) are difficult to interpret when scoring criteria cannot be traced to clinical evidence. Here we developed Med Evidence Bench (MEB; https://www.medevidencebench.org.cn/), comprising 1,536 physician-constructed items across three levels: guideline knowledge, standardized clinical scenarios and real-world laboratory scenarios. Each criterion stating a medical claim is linked to a versioned source-text span. Across ten LLMs, the Evidence Trace Score (ETS) was 0.975-0.997 for guideline knowledge, 0.292-0.658 for standardized scenarios and 0.182-0.447 for real-world scenarios, and rankings varied across levels. For real-world scenarios, scores for identifying clinical information (mean, 0.770) exceeded those for matching evidence (0.165) or formulating recommendations (0.160). On 1,296 criterion-level judgments, automated grading agreed with the majority vote of three physicians (macro-F1, 0.930; 95% confidence interval, 0.915-0.945), although agreement was lower for evidence application. These findings from Chinese-language materials indicate that guideline recall does not ensure patient-specific evidence use and do not establish clinical effectiveness.

cs.CL

版本更新 · v2arXiv:2611.09183

On derandomizing the line-point low-degree test

Prahladh Harsha, Swastik Kopparty, Mrinal Kumar, Ramprasad Saptharishi, Madhu Sudan

原文摘要

We investigate the derandomized version of the classical line-point low-degree test in the high-error regime in the bivariate setting and reveal some unexpected behavior. The classical line-point low-degree test takes an $m$-variate function $f$ over a finite field $\mathbb{F}_q$, queries it along a random line and accepts if the restriction of the function to this line is a low-degree polynomial. The high-error version of (the analysis of) this test asserts that if $f$ has at least $ε$ expected local agreement with a degree-$k$ univariate polynomial on a random line, then in fact $f$ is non-trivially close to some degree-$k$ $m$-variate polynomial even as $ε$ approaches $0$ (provided $q$ is sufficiently large compared to $k$ and $1/ε$). The derandomized version of the problem asks if the same holds when the line is not chosen uniformly over all possible lines but rather from a small set. In this paper we explore the bivariate case ($m=2$). We show, somewhat surprisingly, that there exists a function $f\colon \mathbb{F}_q^2 \to \mathbb{F}_q$ and a set of lines $\mathcal{L}$ in $\mathbb{F}_q^2$ of size nearly $q^{3/2}$ such that on every line in $\mathcal{L}$, $f$ has agreement $\approx 1/2$ on average with some univariate polynomial of degree $k=\sqrt{q}/2$ and yet $f$ is $1 - O(q^{-1/2})$ far from every polynomial of degree $O(k)$. On the positive side, we show that once the field size $q$ is at least $k^2/(ε)^{O(1)}$ such examples disappear and we can get sets of lines of size $O(q/ε^{O(1)})$ on which the low-degree test has a high-error analysis. On the way to our positive result, we show a new high-degree version of the classical two-direction Polishchuk--Spielman divisibility lemma.

cs.CC · cs.IT

版本更新 · v4arXiv:2512.02581

Generative Online Reinforcement Learning

Chubin Zhang, Zhenglin Wan, Feng Chen, Fuchao Yang, Lang Feng, Yaxin Zhou, Xingrui Yu, Yang You 等 10 位作者

原文摘要

Reinforcement learning (RL) faces a persistent tension: policies that are stable to optimize (e.g., Gaussians) are often too simple to represent the multimodal action distributions required for complex control. Conversely, expressive generative policies---such as diffusion and flow matching---can be difficult to optimize in online RL due to intractable likelihoods and gradients propagating through long sampling chains. We address this tension with a key structural principle: decoupling optimization from generation. Building on this, we introduce GoRL (Generative Online Reinforcement Learning), an algorithm-agnostic framework that trains expressive policies from scratch by confining policy optimization to a tractable latent space while delegating action synthesis to a conditional generative decoder. Using a two-timescale alternating schedule and anchoring decoder refinement to a fixed prior, GoRL enables stable optimization while continuously expanding expressiveness. Empirically, GoRL consistently outperforms unimodal and generative baselines across diverse continuous-control tasks. Notably, GoRL achieves returns exceeding 870 on HopperStand, more than $3\times$ the strongest baseline; on high-dimensional humanoid tasks, it further outperforms the strongest non-GoRL baseline by over an order of magnitude. Code is available at https://github.com/bennidict23/GoRL.

cs.LG

新论文 · v1arXiv:2611.13367

No finite rulebook can certify every safe program: an impossibility theorem for gatekeeping AI agents

Tomas Perez-Acle

原文摘要

An AI assistant writes small programs, and a gatekeeper must decide, from the code alone, whether each one may run. Suppose the rules are fixed: never perform a forbidden action, never let the output depend on a secret, always answer eventually. Can two rulebooks, one listing what is allowed and one listing what is not, both be complete, if every rule must be backed by evidence that a machine can check in finite time? We prove that they cannot. Checkable evidence can only establish what a finite record settles, and ``never'' and ``eventually'' are never settled by a finite record. For prohibitions the failure is one-sided: every violation can be caught by watching, but no safe program can be cleared for good. For confidentiality and responsiveness, neither side can be. We characterise exactly which rules about visible behaviour evidence can confirm, and we show that any sound rulebook of $n$ bits omits a compliant program of about $n$ bits. A time limit makes everything checkable, but only by running the program for essentially the whole limit, so a finite machine is not a feasible one. Finally, we show what a gatekeeper can still guarantee: not a verdict on every program, but a checkable list that contains everything it must allow and nothing it must refuse. Simulations on 2.2 million random programs and on self-referential adversaries show that the obstruction is adversarial rather than typical, and that the one error a longer test never removes is the liveness part of confidentiality.

cs.AI · cs.CR

版本更新 · v2arXiv:2601.19704

Robust Joint Power Allocation and Antenna Placement for Pinching-Antenna Systems under Gaussian Location Uncertainty

Hao Feng, Ming Zeng, Xingwang Li, Wenwu Xie, Nian Xia

原文摘要

Pinching antenna systems (PASS) have attracted much attention recently owing to their capability to maintain reliable line-of-sight communication in high-frequency bands. By guiding signals through a waveguide and emitting them via a movable pinching antenna, PASS enable dynamic control of signal propagation and spatial adaptability. However, their performance heavily depends on effective resource allocation, including power allocation and antenna positioning, which becomes challenging under user localization uncertainty. Existing studies largely assume perfect user locations, while our prior work considered uniformly distributed localization errors. In this paper, we develop a robust resource allocation framework for multi-user downlink PASS under Gaussian-distributed localization uncertainty. An energy-efficiency (EE) maximization problem is formulated subject to probabilistic outage constraints, and the minimum transmit power is analytically characterized for any given antenna position. For the unbounded Gaussian model, we prove that the resulting one-dimensional antenna-placement objective is convex and derive a globally optimal derivative-bisection algorithm. We further consider a circularly truncated Gaussian model for bounded localization-error regions and develop a deterministic branch-and-bound method that returns an $ε_{\rm B}$-globally optimal antenna position. Finally, we discuss how position-dependent waveguide attenuation modifies the placement objective and may destroy its convexity. Simulation results verify that the proposed branch-and-bound solution closely matches the bounded grid-search benchmark, demonstrate substantial EE gains from optimized pinching-antenna placement over the bounded fixed-antenna architecture, and reveal an increasing distinction between the bounded and unbounded Gaussian models as the location uncertainty grows.

cs.IT

新论文 · v1arXiv:2611.13236

NCP: Verifier-Guided Optimization of Weight-Space Control Policies

Ekrem Aksoy

原文摘要

We present the Neural Control Plane (NCP), a closed-loop system that observes language-model execution, synthesizes candidate weight-space intervention rules, evaluates them, and maintains a versioned table of admitted policies. NCP separates a pretrained model's inference data plane from the control policy that selects temporary parameter interventions. W-ISA supplies transactional execution and parameter restoration; NCP supplies telemetry, candidate synthesis, admission criteria, priorities, and rule lifetime management. The optimization state consists of active rules and an archive of evaluated candidates, while base-model parameters are restored after each request. In a local SmolLM-135M-Instruct experiment, NCP generated three candidates from development telemetry and evaluated them on separate task examples and a 4,095-target WikiText-2 slice. One projection reduced validation token repetition from 0.4133 to 0.2191, with a perplexity change of -0.0574%. All candidates produced zero newly correct exact answers, so the configured admission gate archived all three and retained the original active policy. Fresh-process repetition and saved-table resumption reproduced the measured outcomes. NCP provides an executable framework for studying recursive self-improvement at the control-policy level through explicit synthesis, verification, and state transitions.

cs.AI

版本更新 · v2arXiv:2603.20827

Swim2Real: Vision-Language Models for Simulator Calibration of a Soft Robotic Fish

Kevin Qiu, Kyle Liam Walker, Mike Yan Michelis, Marek Cygan, Josie Hughes

原文摘要

Calibrating a soft aquatic robot simulator requires matching coupled deformation and propulsion from limited pool recordings. Swim2Real uses a vision-language model (VLM) to compare real and simulated swimming videos and propose updates to 16 simulator parameters. A backtracking line search tests each direction and accepts updates that reduce marker error. To test whether the proposals carry useful directions, we compare them with random and signed-permuted directions under the same line search and simulator budget. In an independent, preregistered fifty-seed replication, Swim2Real reduces the mean best-so-far error over 40 simulator evaluations by 63.4 mm against random directions and 53.2 mm against permuted directions. Both paired comparisons pass Holm correction ($p<10^{-5}$), conditional on run completion. A 24-seed experiment with a second VLM supports the same direction effect. Backtracking averages 16.1 VLM proposals per run versus 39 for Vid2Sid, which attains lower error at the same simulator budget. Ten hardware trials demonstrate open-loop execution of simulator-generated motor commands. Project page and videos: https://swim2real.github.io.

cs.RO

新论文 · v1arXiv:2611.12406

REAL: Reward Modeling through Evidence-Linked Analysis of Lifelikeness in Generated Speech

Yaodong Song, Jie Lian, Xusheng Yang, Genliang Zhao, Hongjie Chen, Jian Kang, Zhen-Hua Ling, Jie Li 等 9 位作者

原文摘要

As modern text-to-speech systems become increasingly intelligible and natural, evaluation is shifting from detecting gross synthesis failures to identifying subtle departures from lifelike human delivery. Because large-scale listening tests are costly and slow, speech reward models can serve as scalable automatic judges for comparing generated utterances, curating data, and supporting iterative TTS development. Existing speech reward models can predict scores or pairwise preferences and may generate natural-language rationales, but their supervision is typically defined at the utterance or pair level. The connection between local acoustic phenomena and the final preference therefore remains implicit. We introduce REAL, a framework for Reward modeling through Evidence-linked Analysis of Lifelikeness in generated speech. Its central idea is to supervise not only the final pairwise preference but also a structured account of its supporting observations, linking local audio spans to perceptual phenomena, affected dimensions, and the overall judgment. Specifically, REAL-Jury constructs these evidence-linked reports through timestamp alignment, multi-model analysis, and dispute-oriented deliberation. REAL-Judge learns to generate them from paired audio inputs. REAL-Eval assesses preference prediction in two tiers, from salient perceptual differences to subtle distinctions among strong TTS systems. Instantiated with MiMo-Audio, REAL-Judge improves pairwise preference accuracy over its backbone by 16.01 and 11.41 percentage points on the two tiers, respectively, and outperforms the open-source speech reward models SpeechJudge and UniSRM on both tiers.

eess.AS · cs.SD

版本更新 · v4arXiv:2505.24622

Rule Forest: Interpretable Ensembles of LLM-Generated Questions for Rare-Outcome Prediction

Ben Griffin, Aaron Ontoyin Yin, Diego Vidaurre, Ugur Koyluoglu, Joseph Ternasky, Fuat Alican, Yigit Ihlamur

原文摘要

Many high-stakes screening decisions in finance amount to predicting a rare outcome from unstructured text, such as whether a founder will successfully build a large company, or which crowdfunded loan will fail to attract funding. When positives are this rare, simple models may be preferable to more complex ones. For example, a model that learns a weight for each feature may have too little signal to estimate those weights reliably, and also inspecting the model means reading a list of fitted coefficients rather than a simple rule that can be checked by eye. We introduce Rule Forest, which uses a large language model to generate simple YES/NO questions, rather than using it to directly predict outcomes, and combines the strongest questions into an equal-weight "green-flags" scorecard. This scorecard is as accurate as an equivalent model that learns a weight per question, within noise, and its advantage appears largest when positives are rarest. The result is an interpretable list of rules that a domain expert can edit and extend. When predicting founder success, the fraction of shortlisted founders who succeed increases from about 1 in 50 to 1 in 10, and to about 1 in 6 with a handful of expert-written questions. A second dataset which focuses on identifying failed loans, Kiva microloans, shows the same qualitative pattern. Across both tasks, the lesson is the same: a language model is most useful not as the predictor but as a generator of features a person can read, edit, and improve, and when positives are scarce that interpretability costs no measurable accuracy.

cs.AI · cs.LG

新论文 · v1arXiv:2611.11833

Answer or Defer? Testing VLMs' Stated Confidence on Brain MRI

Amir Sabbaghziarani, Parsa Ghazvinian, Sepehr Salem, Sergey Plis

原文摘要

Vision-language models (VLMs) could support medical-image interpretation, but their use requires deciding which interpretations to accept and which images to refer to a clinician. We test whether thresholding stated confidence can retain useful coverage while limiting errors among accepted answers, and how this depends on the population. Eight open-weight VLMs, including two reasoning models, assess 3,888 brain MRI slices from post-treatment glioma patients (BraTS 2024) and healthy volunteers (IXI) for tumor or gross abnormality. BraTS labels are mask-derived; IXI slices are treated as negatives. On BraTS, no threshold selects a nonempty set with at most 5% empirical error for any model, even when chosen retrospectively. This also holds for four models evaluated on a large-lesion, distant-negative subset. At a 10% error budget, Gemma-4-12B retains 24.4% of slices and every other model at most 2.5%. To investigate this limited selection ability, we separate confidence differences between predicted answers from differences within each answer. For four models with available outcome-level summaries, pooled mean confidence differs more between answers than between correct and incorrect responses within each answer. A covariance decomposition explains how this pattern can produce opposite confidence-correctness associations across populations. At a 20% error budget, accepting every "tumor" answer covers more slices than any confidence threshold for two models. These findings caution against using unvalidated stated confidence as a standalone deferral signal and support population-specific validation before deployment. Code is available at https://github.com/amir-sbg/VLM-Answer-or-Defer.

cs.CV · cs.AI · cs.LG

版本更新 · v2arXiv:2610.12468

DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training

Junyan Li, Ruizhi Li, Yu Liu, Xiangshuo Liu, Mingchao Sun, Hongyu Pan, Mu Xu, Lue Fan 等 9 位作者

原文摘要

We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a model on existing robot datasets faces two obstacles: imprecise calibration can impair action following, while limited coverage of unsuccessful interactions can bias predictions toward successful outcomes. To improve action following across embodiments, we render action trajectories into image-space conditions and introduce offline geometric calibration to align these conditions with the target videos. To broaden interaction coverage, we introduce counterfactual post-training, modifying recorded action trajectories and generating future videos under a wider range of actions and contact configurations. To provide feedback on these predictions without paired ground-truth futures, we construct a human-annotated video dataset covering robot, object, and interaction defects and use it to train an embodied video reward model. Its scores guide reinforcement-learning post-training toward more physically plausible interaction outcomes. On AgiBot, DreamTrue attains state-of-the-art action following, while reducing the human-assessed interaction defect rate from from 48.12% to 6.25%. Notably, our model ranks first in the world model track of the AgiBot World Challenge 2026. The project page can be found at https://brave-eai.github.io/DreamTrue.

cs.RO · cs.CV

版本更新 · v3arXiv:2503.00747

LFX: Fusion-Form-Flexible Light Field Modeling for Dense Semantic Segmentation and Salient Object Detection

Fei Teng, Lingxin Huang, Buyin Deng, Kai Luo, Boyuan Zheng, Zheng Fang, Hong Zheng, Kunyu Peng 等 11 位作者

原文摘要

Two distinct light field (LF) observation forms, namely sub-aperture images (S.Aperture images) and focal stack (FS), correspond to two fusion settings: the central image with S.Aperture images (CS) and the central image with FS (CF). Existing LF perception methods are typically form-specific, while a modeling design that can be separately instantiated under either setting remains underexplored. To address this gap, we present LFX, a form-flexible LF perception framework. Here, ``X'' represents the LF observation form, indicating that the one modeling design can be separately instantiated under two fusion settings (CS and CF). Specifically, we propose Field-of-Parallax Angular Subspace Modeling (FoP-ASM), which maps the feature difference between each auxiliary observation and the central image to an observation-specific angular marker. This avoids pairwise modeling among auxiliary observations and form-specific geometric assumptions. Meanwhile, a shared manifold subspace and the associated regularization losses constrain the angular residuals within a common feature space, promoting semantic consistency across auxiliary observations. Extensive evaluations across three LF datasets show that LFX achieves state-of-the-art results across distinct LF forms. Under the S.Aperture images and FS settings, respectively, LFX reduces MAE by 12.12%/20.59% on DUTLF-V2 and by 6.15%/7.69% on HFUT, while achieving the best performance on UrbanLF-real. The source code will be made publicly available at https://github.com/FeiT-FeiTeng/LFX.

cs.CV · cs.RO · eess.IV

新论文 · v1arXiv:2611.11349

AOP-Smart-Finder: A High-Throughput Human-AI Hybrid Framework for AOP Discovery and Evidence Mapping from Large-Scale Literature

Qinjiang Niu, Lu Yan

原文摘要

The rapid growth of scientific literature and the high heterogeneity of biological terminology and mechanistic descriptions make it difficult for researchers to integrate scattered research evidence, identify connections among biological events, and construct mechanistic networks. Here, we developed a high-throughput human-AI hybrid framework, AOP-Smart-Finder, for biological event discovery, relationship mining, and Adverse Outcome Pathway (AOP) construction and evidence mapping from large-scale literature. This framework integrates Large Language Models (LLMs), AOP-Smart retrieval-augmented generation (RAG) technology, and Python-based automation, supporting two analysis modes: one based on a single compound and the other based on a predefined set of biological events. In the di(2-ethylhexyl) phthalate (DEHP) case, the system processed 12,983 articles within 30 min and included 1,093 of them, from which it extracted 1,589 biological events (including 458 official key events [KEs] and 1,131 candidate KEs) and 2,519 key event relationships (KERs). In the amyotrophic lateral sclerosis (ALS) case, the system identified 55 stressors from 437 articles and extracted 278 biological events and 548 event relationships. Following manual curation and Weight of Evidence (WoE) evaluation, a mechanistic network comprising 16 KEs and 23 KERs was ultimately constructed. This framework can either use existing AOPs as knowledge guidance for mechanistic expansion and evidence supplementation, or discover novel event connections and construct mechanistic networks around user-specified research topics. It provides a high-throughput, traceable, human-AI hybrid methodology for complex biological mechanism elucidation and AOP discovery driven by large-scale literature.

cs.CL · q-bio.QM

新论文 · v1arXiv:2611.11131

CrossLiDAR: Controllable Multi-Sensor LiDAR Sequence Generation

Khanh Nguyen, Thomas Walker, Hichem Telli, Carlos de la Torre-Ortiz, Stefano Fiorini, Salah Eddine Bekhouche, Mohammed-En-Nadhir Zighem, Wassim Swaileh 等 9 位作者

原文摘要

High-fidelity LiDAR simulation remains a bottleneck for scalable development and validation of autonomous systems. Existing generators can synthesize realistic scans, but they are typically constrained to a single sensor configuration, offer limited control over structure and geometry, and drift in long-horizon 4D generation. We present CrossLiDAR, a unified transformer-based framework capable of generating controllable and spatio-temporally consistent multi-sensor LiDAR sequences. Our approach leverages a rectified flow objective with a Multi-Modal Diffusion Transformer (MM-DiT) backbone, within a compact latent space of range images. To support multiple LiDAR sensors, an Inter-sensor Module enables interaction across sensors, while a ControlNet-style branch provides structural conditioning (e.g., BEV priors or 3D bounding boxes). For modeling the temporal consistency, CrossLiDAR generates short $N$-frame sequences and extends them autoregressively to improve long-horizon coherence. Our model significantly outperforms state-of-the-art baselines, achieving an average improvement of 29.56\% in JSD and 15.36\% in MMD evaluated on nuScenes and the Waymo Dataset. CrossLiDAR bridges the gap to modern autonomous-driving simulation by enabling calibration-consistent multi-sensor LiDAR rollouts over long horizons for controllable, scenario-based testing.

cs.CV · cs.AI · cs.RO

版本更新 · v2arXiv:2609.29695

EvLink: Source-Grounded Evidence Linking for Graph RAG

Linyao Zheng, Xuhang Shi, Zhifang Mao, Sai Zhou, Shuaixian An, Xiuquan Hou

原文摘要

Graph-based Retrieval-Augmented Generation (GraphRAG) supports multi-hop reasoning by organizing corpora into structured graphs. However, graph reachability often captures semantic association rather than evidence support, so a reachable passage may still fail to justify a required cross-passage transition. We propose EvLink, an evidence-linking retriever that preserves passages as retrievable evidence units and builds evidence-supported transitions between them. EvLink constructs two types of reliable links: relation-grounded evidence links justified by explicit source relations, and endpoint-alignment links serving as sourcebounded fallbacks. For retrieval, we introduce a two-stage retrieval strategy. First, bounded breadth-first search over source-grounded evidence links recovers bridge passages missed by similarity-based methods. Then, evidenceneed mining with noisy-OR coverage refinement selects a compact, non-redundant evidence set satisfying distinct question facets. Experiments on three multi-hop and two simple QA benchmarks show EvLink consistently outperforms leading GraphRAG baselines with average gains of 2.4 R@5, 1.9 EM, and 2.4 F1

cs.IR

版本更新 · v2arXiv:2608.08809

Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers

Yu Wang, Shengyao Zhuang, Xueguang Ma, Zongyu Wu, Jimmy Lin, Vivek Srikumar, Zhichao Xu

原文摘要

A single model scale challenges the flexibility of a production retrieval system: some settings need it faster, others need a smaller index, and the right trade-off changes with the workload. In the context of information retrieval (IR), a transformer-based model can be made smaller in three ways --- using fewer layers, passing fewer tokens through the upper layers, or producing a shorter embedding --- and each way saves a different resource. These options have been studied in isolation, each as its own method with its own code and training setup, which makes them hard to combine or adapt to a new model. In this work, we present Tevatron-Elastic to bring all three under one unified abstraction: a single object names any size the model can run at, and a short schedule lists the sizes to train. Training then produces one checkpoint that serves all of those sizes, and at deployment the user has the liberty to pick any of them. The same abstraction covers both retrievers and rerankers and both encoder and decoder models, as it works through interfaces that Hugging Face transformers already expose; adding a new backbone can be a configuration change rather than a model rewrite. Prior methods --- Matryoshka embeddings, early exit, 2D Matryoshka (Starbucks), and layerwise token compression (LTC) --- become special cases of our unified abstraction. With Tevatron-Elastic, we also propose a new elastic algorithm Matryoshka~LTC (MLTC) to jointly train several token-compression ratios in one retriever checkpoint. To validate our framework, we train 20 checkpoints across three backbones and two tasks: the quality curves are smooth, full-point quality remains close to that of models trained for a single size, and a controlled study confirms the wall-clock speedups. We release the framework and all checkpoints to support elastic retrieval research.

cs.CL

新论文 · v1arXiv:2611.11061

Symplectic Normal Coordinates Flow for Generative Modeling of Hamiltonian Systems

Christopher M. Pierce

原文摘要

In conditioned generative models of physical systems, the densities at different values of the conditioning parameters are often related through symplectic transformations. For stable linear Hamiltonian systems, there exists a symplectic transformation to "normal coordinates" such that the dynamics is reduced to rotations in each phase-space plane. This picture extends to the nonlinear case where, away from resonances, the Birkhoff normal form again consists of rotations in phase space, now with amplitude dependence. In this work, we introduce an invertible symplectic flow layer consisting of amplitude-dependent rotations in learned normal coordinates. We derive the condition under which the nonlinear rotation layer is symplectic and detail an architecture that guarantees it. Experiments are carried out on three conditional generative modeling problems: a synthetic chain of coupled nonlinear oscillators and two problems from accelerator physics. We show empirically that normalizing flows with the new layers achieve competitive or superior negative log-likelihoods compared to baseline flows, with gains that grow with the strength of the nonlinearity on the synthetic system.

physics.acc-ph · cs.LG

版本更新 · v2arXiv:2609.03102

WireSeg-32K: A Physics-Grounded Synthetic Dataset for Wire Instance Segmentation

Zilin Dai, Lehong Wang, Yi Yang, Xiang Fei

原文摘要

Deformable linear objects such as wires and cables are difficult to segment because they are thin, highly deformable, and frequently self-occluded, while large-scale instance-level annotations are expensive to obtain in real scenes. Existing resources either focus on cable tracing or semantic segmentation under constrained settings, or generate visually plausible images without physically grounded wire deformation. We present WireSeg-32k, a synthetic dataset for wire instance segmentation with 32,000 RGB images, instance masks, depth maps, and a complementary real-world test set with annotations. To generate this dataset, we develop DeformX, a co-simulation pipeline that couples Cosserat-rod dynamics with photorealistic Isaac Sim rendering, enabling physically plausible, contact-consistent wire shapes, CAD-based wire assets, and diverse visually grounded scenes. As a simple baseline, LoRA fine-tuning SAM3 on WireSeg-32k alone improves real-world mAP@75 by 10.2% over the off-the-shelf model, showing that physically grounded synthetic data can transfer to real wire perception.

cs.CV

新论文 · v1arXiv:2611.10821

AmodalBox: Automated 3D Bounding Box Annotation under Partial Visibility

In-Jae Lee, Namtae Kim, Robert Exley, Kwonyoung Ryu, Jaesik Park

原文摘要

Recent progress in vision foundation models (VFMs) has made automated open-vocabulary 3D bounding box annotation increasingly feasible by jointly leveraging LiDAR point clouds and images. However, partial observations remain a major challenge in sparse driving scenes, where visible LiDAR points often cover only a small fraction of the object's surface and provide insufficient cues for estimating its full spatial extent. As a result, existing methods often produce mislocalized boxes or leave objects unlabeled. To address this limitation, we propose \textbf{\Ours{}}, an automated annotation framework that leverages image-generated 3D assets as amodal geometric priors for partially observed objects. By establishing correspondences between input images and rendered views of 3D assets, \Ours{} robustly aligns canonical amodal geometry with partially observed world-space LiDAR point clouds. To improve temporal consistency and reduce computational cost, \Ours{} generates a single asset per instance, estimates its metric scale once at a single frame and propagates it across frames for dynamic instances, and aggregates multi-frame observations for static instances. 3D object detectors trained on annotations from \Ours{} improve performance over strong baselines by 14.1 mAP on the nuScenes dataset and by 12.45 AP at IoU 0.5 for the vehicle class on the Waymo Open Dataset (WOD). Our project page is available at: \href{https://oliver0922.github.io/AmodalBox/}{https://oliver0922.github.io/AmodalBox/}

cs.CV