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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 03:11 — 2026-11-22 03:11(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19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。

29,158 已收录论文24,181 AI 相关8,992 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 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.22222

ExplicitIR: Explicit Spatial Policy Fields for All-in-One Image Restoration

Dezhi Zhang, Shangrong Yang, Yudong Liang, Wenjian Wang

原文摘要

All-in-one image restoration aims to recover clean images blindly from inputs with various degradation types and levels using a single model. However, the adaptation policy in most existing methods remains implicitly encoded in feature representations, leaving the restoration decision neither explicitly represented nor independently controllable. Since real-world degradations vary spatially, applying uniform updates across the entire image leads to over-smoothing of clean areas and under-correction of localized degradations. To address these limitations, we present ExplicitIR, which represents the restoration policy as two explicit per-pixel fields: Budget, which determines where and how strongly to update, and Style, which selects between narrow and wide context windows. Specifically, ExplicitIR incorporates a Spatial Policy Estimator (SPE) to predict these fields, explicitly representing the restoration policy and capturing spatially-varying degradations, which are then applied by Policy-Adaptive Decoder Blocks (PADB) through adaptive fusion of narrow- and wide-window responses, enabling independent control and precise local modulation. This design enables spatially-adaptive restoration in a single forward pass, without requiring task labels, prompts, or test-time degradation estimators. Extensive experiments on three-task and five-task benchmarks demonstrate that ExplicitIR achieves performance competitive with the strongest all-in-one baselines.

cs.CV

新论文 · v1arXiv:2611.22221

Subsystem Stabilizer $(r,δ)$-Locally Recoverable Codes: Characterization, Bounds and Constructions

Yaozong Zhang, Sihem Mesnager, Xiaoqiang Wang, Jian Gao

原文摘要

Local erasure recovery limits the number of physical systems accessed to repair a distributed quantum memory. For subsystem stabilizer codes (SSCs), a basic question is whether erasures can be corrected within a prescribed repair set. In this paper, we study subsystem stabilizer $(r,δ)$-locally recoverable codes ($(r,δ)$-SSLRCs), in which each coordinate belongs to a repair set of size between $δ$ and $r+δ-1$ that corrects any set of up to $δ-1$ erasures while preserving the logical subsystem and allowing the gauge subsystem to change. We first characterize local erasure recovery algebraically and apply this criterion to Calderbank-Shor-Steane (CSS) and Hermitian hull constructions for $(r,δ)$-SSLRCs. For $(r,δ)$-SSLRCs, without assuming purity, we derive a redundancy bound for disjoint repair sets, a supported-subspace bound based on supported stabilizer and gauge subspaces, and a mixed counting bound for known erasures within selected repair sets and errors at unknown positions outside their union. For pure $(r,δ)$-SSLRCs with overlapping repair sets, we establish the Singleton-type and alphabet-dependent bounds, together with explicit Griesmer, Hamming, and Plotkin bounds. Moreover, we construct nine classes of $\F_q$-linear pure $(r,δ)$-SSLRCs from maximum distance separable (MDS) stabilizer codes, Reed-Solomon (RS) codes, and linear codes with MDS Hermitian hulls, which are simultaneously optimal with respect to several bounds for $(r,δ)$-SSLRCs.

cs.IT

新论文 · v1arXiv:2611.22219

Fine-Grained Japanese Clinical Named Entity Recognition: A Controlled Comparison of BERT and Open-Weight Large Language Models

Feng Han, Ayako Yagahara, Kenji Hirata, Atsushi Yoshida, Kohsuke Kudo

原文摘要

Background: Generative large language models (LLMs) offer an alternative to encoder-based clinical named entity recognition (NER), but their performance on fine-grained Japanese extraction tasks and sensitivity to generation settings remain uncertain. Methods: We compared two fine-tuned BERT-CRF baselines with nine open-weight LLMs on iCorpus, which defines 113 entity categories. The evaluation used 433 sentences from 36 test documents; 1,672 sentences were used for training. LLMs were evaluated using zero-shot prompting with and without JSON Schema constraints and three-seed QLoRA fine-tuning. Fine-tuned models were assessed under different output-token limits, including 900 and larger model-specific limits of 2,600 or 4,096 tokens. Performance was measured using sentence-level label-surface matching with relaxed and exact-surface F1. Results: The highest zero-shot relaxed F1 was 0.337, compared with 0.836-0.841 for the BERT baselines. At the larger output limits, all eight fine-tuned LLMs with at least 13B total parameters exceeded both BERT baselines (relaxed F1, 0.882-0.914; exact-surface F1, 0.840-0.880). Across three-seed means, increasing the output limit improved relaxed F1 by 0.052-0.085, alongside higher recall and fewer length-limited outputs. JSON Schema constraints changed relaxed F1 by -0.014 to +0.008 among seven models outside the two reasoning-oriented configurations, while medical-general model pairs showed no consistent advantage for medical specialization. Conclusions: On this historical Japanese case-report benchmark, task-specific fine-tuning combined with adequate generation capacity was associated with stronger LLM extraction performance. Output-token limits materially affected comparisons with BERT, whereas enforcing output structure alone did not overcome low zero-shot accuracy.

cs.AI · cs.CL

新论文 · v1arXiv:2611.22218

Learning Optimal Transport Plans Via Autoregressive Token Regression

Ivan Jaen Marquez, Sotirios Panagiotis Chytas, Vikas Singh

原文摘要

Optimal Transport (OT) provides a principled framework for finding the minimum cost coupling between probability distributions. Classical solvers remain the gold standard for this task. At the same time, OT is an ideal testbed for studying whether learning-based amortized models can internalize the structure of OT type problems. Here, ground-truth solutions are available and marginal constraints are explicitly defined. Also, exact discrete solutions have well-characterized sparsity. We describe ToR-OT, a transformer-based model that learns to predict discrete OT plans through autoregressive token regression. We reframe OT into a structured sequence generation task. ToR-OT decodes sparse transport plans as sequences instead of solving an optimization task at test time. We focus on three properties: (a) Zero-shot generalization: pretraining on a large synthetic corpus of OT instances allows a single model to generalize to unseen distribution pairs and heterogeneous cost metrics without retraining, (b) Sparse primal decoding: by exploiting the inherent sparsity in exact discrete OT solutions, the decoder predicts only nonzero entries (avoids dense coupling outputs), (c) Amortized inference: on low-dimensional discrete problems, ToR-OT gives accurate approximate plans and compares favorably with per-instance neural OT baselines. Overall, ToR-OT is not yet a replacement for classical solvers, but a step toward understanding how autoregressive transformers can learn structure of constrained optimization problems like OT.

cs.LG · cs.AI

版本更新 · v2arXiv:2609.39514

Spike-driven Vision-Language-Action Model

Shuai Wang, Malu Zhang, Mingquan Liu, Weihui Dai, Dehao Zhang, Jieyuan Zhang, Yimeng Shan, Zijian Zhou 等 11 位作者

原文摘要

Vision-language-action (VLA) models bridge multimodal understanding and robotic control, advancing the dominant paradigm for embodied intelligence. However, most existing models rely on large Transformers, whose latency and energy costs hinder deployment on resource-constrained platforms. Through sparse event-driven computation, spiking neural networks offer a promising paradigm for high-performance and energy-efficient computing. Here, we propose the first Spike-driven VLA framework enabling end-to-end direct training for robotic manipulation, which mainly comprises three core components. First, we develop spiking visual and instruction encoders for multimodal perception, encoding visual observations and language instructions into sparse, reliable spike representations for subsequent cross-modal fusion. Then, we introduce Multi-Winner Spike Fusion for instruction-guided scene understanding, using bidirectional top-$k$ winner-take-all spike routing to suppress background interference and yield fused memory. Finally, we propose a Spike Action Chunking Transformer that incorporates spiking cross-attention over the fused memory and the current robot state, enabling efficient end-to-end generation of continuous action chunks for robotic control. Extensive experiments on LIBERO and Meta-World demonstrate that Spike-driven VLA achieves competitive performance with fewer parameters and lower estimated inference energy than conventional VLA models. This work establishes a foundational framework for neuromorphic VLA modeling, paving the way for future advances in resource-efficient embodied intelligence.

cs.CL

新论文 · v1arXiv:2611.22216

Settling the Time and Structural Complexity of Bertrand Networks

MohammadTaghi Hajiaghayi, Suho Shin

原文摘要

In the seminal Bertrand network game introduced by Babaioff et al. (2013), each seller posts a single price to captive buyers and to the markets it shares with neighboring sellers, where sellers cannot price discriminate across the markets. Although the existence of equilibria and polynomial-time algorithms to compute them in trees (Babaioff et al. (2013)) have been known, it has been a major open problem whether there exist efficient algorithms to compute them for general graphs. In this paper, we resolve this open question negatively by proving that computing any constant-error approximate Nash equilibrium in a Bertrand network is $\PPAD$-complete. This hardness holds even on sparse bipartite graphs of maximum degree five with constant integer market weights. Complementing our hardness result, we design an efficient polynomial-time approximation scheme (EPTAS) when both the maximum degree and the number of sellers with captive buyers are bounded. Beyond time complexity, since exact equilibria require randomizing prices over continuous intervals, another fundamental question left open by Babaioff et al. (2013) is whether an exact equilibrium can always be represented with a finite number of price intervals, \ie whether its structural complexity is finite. We resolve this question affirmatively by proving that every achievable equilibrium revenue profile can be realized by an equilibrium with structural complexity $O(2^n)$, which leads to an exact algorithm running in doubly exponential time. We further show that this bound is tight: there exist instances for which the unique equilibrium realizing target revenue profiles has structural complexity $Ω(2^n)$.

cs.GT · cs.DS · econ.TH

新论文 · v1arXiv:2611.22215

Communicate the Change: Efficient Expert Parallelism via Activation Compression

Fengyuan Liu, Jay Gala, Siva Reddy, Dzmitry Bahdanau

原文摘要

Scaling has driven the success of large language models (LLM), with sparse mixture-of-experts (MoE) architectures enabling greater parameter capacity without a proportional increase in computation. At large scales, MoE models rely on expert parallelism to distribute experts across devices. Each MoE layer requires two synchronous collective communication steps during inference: dispatching hidden states to the activated experts and combining the resulting expert outputs. As compute throughput has outpaced interconnect bandwidth, these synchronous collectives have become a major bottleneck to MoE scaling and efficiency. We address this challenge with EchoMoE, a lightweight architecture modification that retrofits existing MoE models, requiring approximately 8,500x fewer training tokens than full pretraining. Motivated by the observation that transformer blocks update the residual stream incrementally, we use a hidden state from an earlier layer as a reference and communicate only the compressed difference between it and the current state, rather than communicating each hidden state in full. EchoMoE periodically refreshes these reference states and transmits only the compressed differences synchronously, reducing the traffic on latency-critical paths without significant computational overhead. EchoMoE reduces inter-node communication volume by 58% and improves throughput by 22.6%, while preserving average performance within 3.8 percentage points across 18 benchmarks. EchoMoE further improves inference throughput by up to 2.38x over bandwidth-constrained Ethernet, paving the way for wide-area distributed inference. EchoMoE also tolerates quantization of the communicated representations without measurable quality loss. We release an efficient implementation for applying EchoMoE to pretrained MoE models, together with an inference integration for vLLM.

cs.LG · cs.AI · cs.DC

新论文 · v1arXiv:2611.22212

Joint-ID: Transformer-based Joint Image Enhancement and Depth Estimation for Underwater Environments

Geonmo Yang, Gilhwan Kang, Juhui Lee, Younggun Cho

原文摘要

Underwater imaging is a challenging task due to factors such as scattering, absorption, and turbulence, which degrade image quality and limit visibility. In this paper, we propose a novel approach for enhancing underwater images that leverages the benefits of joint learning for simultaneous image enhancement and depth estimation. We introduce Joint-ID, a transformer-based neural network that can obtain high-perceptual image quality and depth information from raw underwater images. Our approach formulates a multi-modal objective function that addresses invalid depth, lack of sharpness, and image degradation based on color and local texture. We design an end-to-end training pipeline that enables joint restoration and depth estimation in a shared hierarchical feature space. Additionally, we propose a synthetic dataset with various distortions and scene depths for multi-task learning. We evaluate Joint-ID on synthetic and standard datasets, as well as real underwater images with diverse spectra and harsh turbidity, demonstrating its effectiveness for underwater image enhancement and depth estimation. Furthermore, we demonstrate the ability of Joint-ID to perform feature matching and saliency detection for visually guided underwater robots. Our proposed method has the potential to improve the visual perception of underwater environments and benefit applications such as oceanography and underwater robotics. Supplements are available at: https://sites.google.com/view/joint-id/home

cs.CV

版本更新 · v3arXiv:2604.00024

WHBench: Evaluating Frontier LLMs with Expert-in-the-Loop Validation on Women's Health Topics

Sneha Maurya, Spandana Govindgari, Girish Kumar

原文摘要

Large language models are increasingly used for medical guidance, but women's health remains under-evaluated in benchmark design. We present the Women's Health Benchmark (WHBench), a targeted evaluation suite of 47 expert-crafted scenarios across 10 women's health topics, designed to expose clinically meaningful failure modes including outdated guidelines, unsafe omissions, dosing errors, and equity-related blind spots. We evaluate 22 models using a 23-criterion rubric spanning clinical accuracy, completeness, safety, communication quality, instruction following, equity, uncertainty handling, and guideline adherence, with safety-weighted penalties and server-side score recalculation. Across 3,102 attempted responses (3,100 scored), no model mean performance exceeds 75 percent; the best model reaches 72.1 percent. Even top models show low fully correct rates and substantial variation in harm rates. Inter-rater reliability is moderate at the response label level but high for model ranking, supporting WHBench utility for comparative system evaluation while highlighting the need for expert oversight in clinical deployment. WHBench provides a public, failure-mode-aware benchmark to track safer and more equitable progress in womens health AI.

cs.CL · cs.AI · cs.CY

新论文 · v1arXiv:2611.22210

Sample-efficient Personalization of Large Language Model Alignment with Multidimensional User Preference Data

Zhen-Yu Zhang, Jerry Huang, Gang Niu, Takashi Ishida, Masashi Sugiyama

原文摘要

Preference alignment has become a central tool to align large language models (LLMs) with human values and desired behavior, and its online variant can further advance their capabilities beyond what static data alone offer by repeatedly generating and labeling new responses with human feedback. But costly, time-consuming annotations limit its scalability, making sample efficiency essential, and existing methods typically seek to improve it by expanding coverage of the response space or selecting pairs with the highest uncertainty for comparison. Although they are effective, these methods quantify uncertainty from the perspective of the LLM, which may differ from the uncertainty perceived by the user: a pair can appear highly uncertain to the LLM even when past comparisons from the user already imply a clear ordering. In this paper, we propose multidimensional preference-guided online direct preference optimization (MPG-DPO), which leverages low-cost multidimensional evaluations from automated verifiers on the user historical comparisons to construct a personalized preference cone guiding response selection for online preference alignment. Specifically, it first discards responses that are confidently dominated under the estimated user preference, then selects two responses that are competitive under the retained preference cone yet exhibit the strongest unresolved disagreement. Theoretical analysis shows that, with high probability, the fraction of queries spent on cone-dominated responses vanishes as learning progresses. Experiments across multiple LLM families show that MPG-DPO outperforms strong contenders under matched query budgets.

cs.LG

新论文 · v1arXiv:2611.22207

ARG-Avatar: Animation-Rendering Guidance for Efficient Feedforward Avatar Reconstruction

Jianjin Xu, Soham Dasgupta, Fernando De la Torre

原文摘要

Reconstructing animatable 3D human avatars from images is important for applications such as gaming and augmented reality. Feedforward methods make avatar reconstruction accessible by reducing inference time to a few seconds, but recent approaches rely heavily on scaling model capacity, training data, and computation. We ask whether such scaling is necessary. To this end, we introduce ARG-Avatar, an efficient feedforward framework with only 68M trainable parameters that achieves SOTA reconstruction quality. Our key insight is that 3D animation and rendering already provide strong geometric correspondences that existing methods largely attempt to learn from data. In light of this, we design the Foreground Avatar Coordinate RoPE attention (FACRoPE) and Intermediate Token Rendering (ITR) pipeline to guide avatar tokens to attend to their corresponding patches. Experiments across multiple datasets show that ARG-Avatar consistently outperforms prior methods when using two or more input images. Compared with LHM++, ARG-Avatar uses approximately 9$\times$ fewer trainable parameters, 4.8$\times$ fewer training sequences, and 14$\times$ less training compute, while running 6$\times$ faster and achieving a 2.7 dB PSNR improvement on the out-of-distribution NeuMan benchmark.

cs.CV · cs.GR

新论文 · v1arXiv:2611.22205

More lower bounds for Hales--Jewett and van der Waerden numbers

Younes Mouhib

原文摘要

We give explicit colourings improving the comparison lower bounds assembled here for several Hales--Jewett and van der Waerden numbers. The main algebraic tool generalises Rabung's power-residue colouring from arithmetic progressions to arbitrary sets. If every translate of a t-element set S in F_p meets at least two classes of the r-th power character, and the integer weights have both parities, then a period-2p one-weight colouring of [t]^p has no monochromatic combinatorial line. The 19 displayed algebraic certificates comprise 18 improvements and one closed-form reproduction; they include HJ(4,3)>=164, HJ(5,4)>=7418, and HJ(5,6)>=34034. The underlying period-p construction also proves kappa_ow(t,r)>=p-1 for the one-weight bracket ceiling, in particular kappa_ow(5,4)>=7416 and kappa_ow(5,6)>=34032. Warm breakout-weighted tabu search on the type simplex gives HJ(3,4)>=51. Whole-colouring local search gives W(8,3)>522, W(11,3)>1193, and W(17,3)>3620. All accepted certificates are available separately and are checked by direct enumeration; unresolved searches are reported as UNKNOWN, not UNSAT.

math.CO · cs.DM

新论文 · v1arXiv:2611.22206

TAILROLL: Tail-Aware Rollout Acceleration for RL-Based LLM Post-Training

Niloofar Gholipour, Marcos Assuncao, Timothy Yu, Gursimran Singh, Rajkumar Buyya, Julien Gascon-Samson, Zhenan Fan, Yong Zhang

原文摘要

RL post-training of large language models (LLMs) is bottlenecked by rollout: heavy-tailed responses leave engines idle as each step waits for the longest response. Asynchronous training masks, but does not eliminate, idle time. We distinguish imbalance waste (uneven placement and decode contention) from straggler waste (waiting for the longest response). Tail length, not average load, often sets the step bound. We propose TAILROLL, an online scheduler integrated into an open-source RL framework. It combines stateless in-flight migration and sufficiency-gated termination. Migration moves decoding requests between engines at chunk boundaries and resumes them with one re-prefill under a freeness-based, cost-aware tail-balancing policy. Termination stops a response when its GRPO group has enough completed samples for advantage estimation, masking its partial output from the training loss. Across ten configurations, TAILROLL reduces rollout bubble ratio by 21% to 74% and cross-engine KV-cache imbalance by 44% to 79%. In end-to-end RL training, it cuts rollout time by 24% to 34%, full step time by 21% to 22% on long-CoT RL, and p95 request latency by 28% to 37%, while raising generation throughput by up to 33% with comparable or higher final reward.

cs.DC

版本更新 · v2arXiv:2611.11739

Why Kubernetes Cannot Contain a Full Lazy-Pulling Cache: Two Impossibility Results and a Bounded, Honest Design for Model Serving

Georgii Kliukovkin

原文摘要

Lazy container-image pulling makes cold starts of autoscaled model-serving fleets on Kubernetes nearly independent of model size, but it moves the model's bytes into a node-level cache that the platform neither bounds nor accounts for. This article establishes, by experiment, two impossibility results for that cache. A monitoring-side remedy cannot catch its failure: a sentinel readiness probe stays green while 272 of 280 files are unreadable. A platform-side remedy cannot contain it: kubelet, given full disk-pressure visibility, frees 0 bytes by image garbage collection and falls back to evicting pods (26 across the campaign, the reading pod among them), because its reclamation actuator is keyed to an accounting that does not know the cache exists. The article then eliminates the failure class inside the component that owns the bytes, with no change to kubelet or the container runtime interface, by two design rules: a byte budget whose pressure signal is keyed to filesystem truth, so that a never-blocking, lossy accounting still enforces a hard bound (held against about 301,000 dropped updates), and pass-through semantics under which a failed cache write never becomes a failed read, with the coupling traced to a single io.MultiWriter. Across six pre-specified campaigns on AWS, upstream stargz-snapshotter fails 273 of 280 model files at 90% cache pre-fill; the proposed system reads all 150.3 GB with zero errors at +18.5% completion cost and holds the budget under a live read, co-tenancy, and a three-node fleet. A source audit shows the missing bound generalizes to SOCI and Nydus. The implementation is open source and has been proposed upstream.

cs.DC · cs.OS · cs.PF

新论文 · v1arXiv:2611.22204

Flocking Time and Graph Volume in Nonlinear Cucker-Smale Models with Dynamic Networks

Sooyeon Song, Jea-Hyun Park

原文摘要

This study proposes a Cucker-Smale model incorporating dynamic networks and the discrete $p$-Laplacian ($p \in (1,2)$) and analyzes the relationship between flocking time constraints and graph connectivity from both theoretical and experimental perspectives. We establish that this model achieves flocking within finite time and derive a quantitative relationship between the lower bound of flocking time and graph volume. Based on these results, we observe that imposing sufficiently small flocking time induces an increase in network volume, and that larger initial velocity variance requires greater volume under the same time constraint. In our experiments, we trained a transformer-based PPO policy to select network structures at each time step. Under the most stringent time constraint, the maximum average number of connections increased sharply, confirming a threshold effect. The negative correlation between convergence time and average number of connections reflects the theoretical results well. This study provides quantitative evidence for the phenomenon that time constraints induce connection mobilization.

math.DS · cs.LG · nlin.AO

版本更新 · v2arXiv:2507.14812

A Black-Box Approach for Exogenous Replenishment in Online Resource Allocation

Suho Kang, Ziyang Liu, Rajan Udwani

原文摘要

In a typical online resource allocation problem, we start with a fixed inventory of resources and make online allocation decisions in response to resource requests that arrive sequentially over a finite horizon. We consider settings where the inventory is replenished over time according to an unknown exogenous process. We introduce black-box methods that extend any existing algorithm, originally designed without considering replenishment, into one that works with an arbitrary (adversarial or stochastic) replenishment process. Our approach preserves the original algorithm's competitive ratio in regimes with large initial inventory, thereby enabling the seamless integration of exogenous replenishment into a large body of existing algorithmic results for both adversarial and stochastic arrival models.

cs.DS

新论文 · v1arXiv:2611.22200

MIRAGE: Motion Identity Reduction via Autoregressive Generative Encoding for Privacy-Preserving Skeleton-based Motion Data

Thomas Carr, Xujun Che, Depeng Xu, Shuhan Yuan, Aidong Lu

原文摘要

Skeleton motion identifies people through body proportions and movement style, and skeleton streams are increasingly passed to third-party analytics that run action classifiers trained on raw data. A prior adversarial anonymizer adds a per-frame residual in the raw coordinate space but sees one frame at a time; motion retargeting needs a target skeleton and complete sequences, which rules out online use. We present MIRAGE, a target-free, causal anonymizer that adds an identity-reducing residual to each incoming frame in the raw coordinate space, computed by attention over past frames. One causal, optionally windowed mask governs every attention in a rotary-position encoder-decoder, and key/value caches let the trained function run frame by frame; on all 56,578 NTU 60 sequences, batched and streaming outputs differ by at most 7.2e-6 m. Reported results use an unbounded window, so per-stream state grows with stream length. We evaluate against a passive adversary that applies raw-trained identity models and an adaptive adversary that trains on the anonymizer's output, treating the adaptive adversary as the headline, on NTU RGB+D 60 over five generator seeds, alongside the per-frame residual anonymizer of Moon et al. trained identically. When consumers retrain on the released data, MIRAGE keeps 83.9% action recognition (raw 89.1%; Moon et al. 88.7%) while a retrained identity classifier reaches 43.4% re-identification (RI) over 40 subjects, against 69.4% for Moon et al. and 75.4% on raw data. The strongest adaptive attacker still reaches 49.3% (chance 2.5%), so MIRAGE reduces identity leakage; it does not anonymize. Against raw-trained (frozen) classifiers, MIRAGE lowers RI below the strongest retargeting baseline (10.36% vs. 22.09%), but frozen action recognition falls to 37.04% (vs. 75.82%), so at full residual scale it is not a drop-in replacement for raw input to existing frozen models.

cs.CV

版本更新 · v2arXiv:2608.13087

Sampling Luck Masquerades as Allocation Gain: Auditing Test-Time Budget Allocation for Neural Combinatorial Optimization

Jinhyung Bae

原文摘要

Neural combinatorial optimization (NCO) solvers report the best of many sampled solutions per instance, and the sample count is, by convention, identical for every instance. Whether a non-uniform allocation of a fixed total budget would buy anything has not been measured. We measure it, and we audit the measurement itself. First, on in-distribution workloads the allocation headroom is not detectable. Across three pretrained solvers (POMO, AM, SymNCO) on uniform TSP-100, an oracle allocation computed and evaluated on the same stored samples reports a 2.2-2.6% gain with intervals excluding zero; measured out of sample the same gain is indistinguishable from zero (0.457, 0.015, -0.512 percent). Following the customary in-sample procedure, all three solvers would have supported a published 2%-level gain that does not exist. We calibrate this bias against an instance-wise null in which the true gain is zero by construction; over the ranges we test it does not shrink with more samples or more instances. Second, the same correction that removes the phantom gains preserves a real one. Under distribution shift (a workload mixing uniform and clustered instances), a pre-registered confirmatory experiment finds that allocation guided by held-out sample statistics improves best-of-k by 11.5% (AM, primary endpoint; 95% CI [7.4, 19.7]) and 12.0% (SymNCO, replication) at equal evaluation budget, with the signal-acquisition cost not charged; a pre-registered negative control (POMO, an order of magnitude more robust to shift) shows -0.3% [-0.7, 0.24]. The gain exceeds a frozen distribution-label baseline by 4.2 points [1.9, 7.7]. An exploratory policy charging a 20-sample probe against the same budget retains 3.4% (AM) and 4.6% (SymNCO). We give a correction procedure and a reporting checklist, and release all data, code, and the pre-registration record.

cs.LG · cs.AI · math.OC

新论文 · v1arXiv:2611.22195

Haptic Probing for Subsurface-Aware Force Distribution on Layered Soft Tissue

Lei Shi, Xiaoyu Wang, Cheng Zhou, Yongjian Liu, Jing Wang, Dongsheng Zhang, Yonghui Zhu, Xiong Li

原文摘要

Force-regulated contact with layered soft tissue fails most often where the subsurface composition changes: controllers infer the substrate from the loading signal alone, so the estimate guiding them lags the change---more acutely, we argue, over compliant than over bone-backed tissue. We remove that lag with a separate haptic channel. Under a light preload, a brief low-amplitude excitation lets the local dynamic admittance discriminate muscle from bone-backed tissue relative to a per-subject baseline, before task force is applied---active haptic sensing used to commit a control decision rather than to characterise tissue. A force- and tactile-driven distribution law then consumes that regime throughout execution: an instantaneous allocation equalises pressure across the engaged fingertips, while the regime sets the admissible pressure and hence the area the hand must recruit to deliver the target force---making patch area a controlled variable rather than a by-product. Probing, switches and recruitment are priced in a partitioned passivity budget, so safety monitoring cannot suppress the probe and a refused recruitment forfeits force tracking rather than the pressure bound. We report force tracking and pressure uniformity over curved, migrating contact on three human subjects, with regime labels from anatomical landmarks.

cs.RO

版本更新 · v3arXiv:2603.01608

Evaluating and Understanding Scheming Propensity in LLM Agents

Mia Hopman, Jannes Elstner, Maria Avramidou, Amritanshu Prasad, David Lindner

原文摘要

As frontier language models are increasingly deployed as autonomous agents pursuing complex, long-term objectives, there is increased risk of scheming: agents covertly pursuing misaligned goals. Prior work has focused on showing agents are capable of scheming, but their propensity to scheme in realistic scenarios remains underexplored. To understand when agents scheme, we decompose scheming incentives into agent factors and environmental factors. We develop realistic settings allowing us to systematically vary these factors, each with scheming opportunities for agents that pursue instrumentally convergent goals such as self-preservation, resource acquisition, and goal-guarding. Across 11 frontier models and four scenarios, we find almost no scheming despite high environmental incentives, and show this is unlikely to be explained by verbalized evaluation awareness. While inserting adversarially-designed prompt snippets that encourage agency and goal-directedness into an agent's system prompt can induce high scheming rates, snippets used in real agent scaffolds rarely do. In model organisms built with these snippets, scheming behavior is brittle: removing a single tool can drop the scheming rate from 59% to 3%. Increasing oversight can raise rather than deter scheming by up to 25%, an effect that depends on the wording of the oversight sentence and does not appear in a second scenario, where the sabotage itself is reviewed. These results suggest that scheming propensity should be reported per agent configuration rather than as a single rate. Our incentive decomposition enables such systematic measurement in settings relevant for deployment, which is necessary as agents are entrusted with increasingly consequential tasks.

cs.AI

新论文 · v1arXiv:2611.22190

Emergence and Collapse of Leader-Follower Flocks through Phantom Targets: Surprise Nullification in Bayesian and Inverse Bayesian Inference

Shuji Shinohara, Daiki Morita, Yoshihiro Nakajima, Takeshi Takano, Masakazu Higuchi, Ung-il Chung, Yukio-Pegio Gunji

原文摘要

In Bayesian and inverse Bayesian (BIB) inference, a large prediction error can trigger surprise nullification, which expands belief and likelihood variances by a common factor, leaving the updated variance ratio the same as in standard Bayesian updating. This can increase belief uncertainty while keeping the learning rate low. In the simulations, three agents used BIB inference to predict one another's positions and moved toward those predictions, repeatedly forming leader-follower flocks that subsequently collapsed despite having no alignment rules or designated leaders. Three leadership criteria (front position, heading stability, and flock initiation) identified the same agent in 89% of eligible flocks, with different agents serving as leaders across flocks. Flocks formed when an agent nearly stopped incorporating another's observations (link cut) and moved straight toward a predicted position detached from reality (phantom target), thereby attracting followers. Link cuts arose when two successive resets assigned a very small and then an ordinary likelihood variance, sharply increasing the likelihood-to-belief variance ratio. Flocks collapsed upon link recovery or when returning phantom targets balanced the leader's forward and backward attractions. Without nullification, cuts persisted throughout the analysis period; expanding only belief variance caused recovery within a few steps. Expanding likelihood variance as well allowed cuts to persist while belief uncertainty grew, enabling later resets and recovery. Thus, nullification preserves relative precision, allowing cuts and flocks to persist, while reducing absolute precision to enable recovery and collapse, reconciling these seemingly opposing processes through a single operation. These results suggest that, in this model, individually inaccurate predictions can give rise to collective order.

cs.MA · nlin.AO

版本更新 · v3arXiv:2606.11722

ICA Lens: Non-Gaussianity Reveals Interpretable Directions in Language Models

Sida Liu, Feijiang Han, Sarah Wiegreffe, Furong Huang

原文摘要

Finding human-interpretable directions in language-model activations is important for understanding and controlling model behavior. These directions are usually discovered through indirect learning objectives such as sparse reconstruction, but it remains unclear what existing statistical structure distinguishes interpretable directions and whether that structure can be used directly for feature discovery. We find that non-Gaussianity provides such a signature: projection distributions of natural-text residual-stream activations along sparse autoencoder (SAE) decoder directions are substantially more non-Gaussian than those along random directions, with most contexts forming a concentrated background and recurring patterns often occupying one tail. This raises a natural question: if interpretable directions tend to have non-Gaussian projection distributions, can we discover them by searching for non-Gaussian directions directly in activation space, without training another sparse dictionary? To test this hypothesis, we introduce ICA Lens, a practical workflow for efficient discovery, reliable annotation, and faithful evaluation of non-Gaussian directions in LLM residual-stream activations. Across GPT-2 Small, Gemma 2 2B, and Qwen 3.5 9B Base, we find that (1) the recovered non-Gaussian directions capture coherent lexical, syntactic, and semantic patterns under both human and LLM-based evaluation; (2) non-Gaussianity is positively associated with both human-label confidence and automated interpretability; and (3) the resulting coordinates are competitive with SAEs across interpretability, sparse reconstruction, concept prediction, and causal interventions, while fitting in minutes per layer and using 7-43 times less memory. These results show that non-Gaussianity is a direct unsupervised signal for discovering interpretable and useful structure in activations.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.22186

Is 4-Bit Quantization More Than Noise to a Chat Model's Safety Behaviour? Attributing Behavioural Shifts with Matched Perturbations

Ege Kaya

原文摘要

Chat models on phones and laptops are usually 4-bit copies of the model that was evaluated, and audits of such copies disagree about what quantization does to refusal. A 4-bit build is one of many weight perturbations of the same size, so a change in its behaviour could come from its specific rounding error or from any perturbation that large. In a pre-registered study of three 3-4B chat models, with paired tests, blind human labels and an 8-bit null, we find two 4-bit shifts of opposite sign: with a compliant reply prefilled, Qwen2.5-3B continues into harmful content more often, and on held-out jailbreaks Llama-3.2-3B complies 10.3 points less often. Matched perturbations separate the two. Shuffled and Gaussian versions of the error average close to zero, while scaling the real error, from its mirror image to twice its size, changes behaviour near-linearly. At half the real error, Llama's likelihood is almost unchanged, yet it already complies 5.8 points less often, and llama.cpp's Q4_K_M, at the same bits per weight, moves neither model. Refusal under 4-bit quantization depends on the specific rounding error, not on bits per weight or likelihood, so each build has to be compared with its original.

cs.CR · cs.CL

版本更新 · v2arXiv:2504.07927

Physics-Aware Zero-Shot Learning for Low-Dose CT from a Single Sinogram

Yongyi Shi, Siming Lu, Yongfeng Gao, Hao Zhang, Hengyong Yu, Ge Wang

原文摘要

Low-dose computed tomography (CT) imaging remains a persistent challenge, especially under heterogeneous acquisition conditions. Zero-shot learning, which enables models to learn directly from individual images without external supervision, represents a compelling approach to mitigate distribution mismatches arising from variations in scanner hardware, imaging protocols, and patient demographics. However, most existing zero-shot approaches employ down-sampling operations that reduce spatial resolution and cause domain shifts, which become particularly evident when applied to raw sinogram data. Here, we propose a physics-aware zero-shot CT denoising framework to exploit the conjugate symmetry property intrinsic to CT sinograms. Conjugate X-ray pencil beams traverse identical anatomical paths and ideally yield the same expected attenuation values but with independent noise realizations. By randomly mapping sinogram values between conjugate-ray pairs, we synthesize structurally consistent yet noise-diverse sinogram pairs, enabling self-supervised network training without external data. The resulting lightweight denoising network demonstrates strong generalization across low-dose simulation, clinical helical CT, and preclinical photon-counting CT datasets. Quantitative and qualitative results demonstrate competitive denoising performance, with favorable noise suppression and structural preservation across diverse acquisition settings. This work establishes a generalizable and data-efficient paradigm for CT denoising that integrates physical redundancy into learning-based image reconstruction. The code for the proposed method is openly available at: https://github.com/shiyongyi/Physics-Aware-Zero-Shot-CT-Sinogram-Denoising

eess.IV · cs.CV

新论文 · v1arXiv:2611.22183

A Compilation Model for Divergent Parallel Workloads

Alexander J Root, Christophe Gyurgyik, Devanshu Ladsaria, Rohan Sawhney, Jonathan Ragan-Kelley, Andrew Adams, Matt Pharr, Kayvon Fatahalian 等 9 位作者

原文摘要

Efficient execution on modern parallel machines requires more than abundant parallelism; it demands instruction coherence, memory coherence, and load balance to maximize SIMD utilization and memory bandwidth. Efficiently mapping \textit{divergent} parallel workloads to modern machines, where control flow, memory accesses, and unbounded iteration depend on per-thread runtime values, often requires global program restructuring that trades off increased coherence with reduced locality, parallelism, or extra work. We observe that the key optimizations used to accelerate divergent parallel programs can be expressed as compositions of well-known program transformations from the functional programming and loop optimization communities. We operationalize this insight through \textit{parallel dispatch graphs}: a compilation model that represents divergent programs by representing control flow, data flow between logical stages, and parallel loops within a single abstraction. To facilitate rapid exploration of points in the optimization space, we provide a scheduling language that includes composable transformations of data-dependent control flow and data flow, together with standard loop transformations and hardware bindings. This separation of concerns allows the core algorithm to remain portable, while the execution schedule can be specialized to the specifics of target hardware and input data values. We evaluate our system using popular applications from the domain of spatial computing, and show that the optimization strategies of hand-optimized parallel tree traversals, path tracers, and Monte Carlo PDE solvers can be reproduced as schedules in our system. Our generated code matches or outperforms the hand-optimized implementations (geomeans $1.02$--$2.95\times$ faster). Additionally, we demonstrate empirically that the best schedule varies across programs, machines, and inputs.

cs.PL

新论文 · v1arXiv:2611.22180

CueClash: Frontier Vision-Language Models Judge 3-D Relations Close to the Picture Plane

Soham Dan

原文摘要

A vision-language model (VLM) can judge 3-D relations from the picture or from the ground layout. In photographs the two usually agree. We separate them with CueClash, rendered scenes in which the 2-D cue for each of five relations is right on exactly half the statements. The shortcut gap is accuracy when the cue is right minus accuracy when it is wrong. For Claude Opus 5.5, GPT-5.5 and Gemini 3.6 Flash at low reasoning effort it is +18 to +37 percentage points. It is +7 to +29 without two relations whose cue-wrong items are confounded with borderline cases or occlusion. Given ground coordinates and each relation's definition, they answer 99 to 100% correctly. Pixel measurements with camera depths remove most of the gap for objects fitting through openings. The failure lies in the step from the picture to the layout. The maps that the models draw of the scene from above mostly keep the depth order but, like the picture, shorten depth. GPT-5.5's maps stay close to a copy of the picture. Opus 5.5's and Gemini's maps undo about 0.6 of this shortening. Gemini's then shrink all depths by a further uniform factor. Opus 5.5 follows the picture mainly on fits, and its maps correct depth about as much as human observers of real scenes do. The three models also lose accuracy on CV-Bench photographs where a reliable 2-D cue misleads. In two open models the layout information reaches the language model, but their maps lose much of it.

cs.CV · cs.AI · cs.RO

新论文 · v1arXiv:2611.22179

RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn't

Jingyu Liu, Zongze Li, Zach Xu, Zhanhui Zhou, Tahseen Rabbani, Dawn Song, Ce Zhang

原文摘要

Agentic memory research has accumulated extraction, supersession, reflection, and graph synthesis on top of retrieval-augmented generation. However, we found that almost none of those primitives earn their cost in our tested memory benchmarks: we show this with BRIDGE, a deliberately minimal RAG memory with chained observation notes, hybrid BM25 with cosine retrieval, and chronological rendering, which reaches parity within bootstrap CI with the prior SOTA on LongMemEval-S and BEAM, and beats the best memory baseline on EverMemBench by 5.7-6.3 points at matched reader. It runs at ~5-7K reader-prompt tokens per query, using a single LLM call for each ingestion or query. We argue that this parity is itself the result: standard benchmarks score what memory retrieves, not what memory enables when the agent acts. To test the latter, we introduce five adversarial probes (Rule Application +-, Pattern Induction Style / Procedural, Dynamic Multiturn) judged at generation time by a cross vendor verification chain, where each query can only be solved by applying a remembered rule or pattern it never mentions. Across 5 probes x 20 scenarios, no architecture wins universally: atomic fact extractors (LangMem) win rule application, while BRIDGE's block-summary memory wins pattern induction. This result holds across four domains, three graders, and three reader families. Each design fails where the other wins, for reasons a recall benchmark cannot see: atomic-fact extractors discard the form a demonstrated pattern takes, while block-summary memory retrieves the rule but the reader does not act on it, a gap that presenting the rule more prominently largely closes. What separates memory designs is not what they retrieve but what they enable an agent to do, and that is what agentic memory should be evaluated on.

cs.AI

版本更新 · v2arXiv:2608.24089

CodeHID: Learning an Addressable Hierarchical Code Index for Generative Code Retrieval

Zhen Li, Yuhong Chen, Wenhao Xu, Xiaodong Li, Hui Li

原文摘要

Code retrieval models have predominantly relied on a flat matching paradigm that treats code snippets as independent candidates, making them less capable of distinguishing similar code candidates. Generative retrieval offers a solution by constructing a learnable index over the code corpus, guiding the retriever to better understand how code candidates are semantically organized and addressed. However, naively applying generative retrieval in the code retrieval task may result in operating over an identifier space whose prefixes do not correspond to meaningful code-semantic regions. In this paper, we propose CodeHID, a generative code retrieval framework that reformulates the code retrieval task from flat candidate matching to coarse-to-fine semantic address generation. CodeHID relies on two core components. First, Pseudo-Neighbor Guided DocID Learning constructs a globally static hierarchical index by applying multi-level residual quantization and $k$-nearest-neighbor pseudo-supervision, ensuring that semantically related code snippets share prefixes while preserving target-level separability. Second, Dual-Phase DocID Generation Guidance reliably navigates this fixed index by combining training-side ranking enhancements, using hard negatives and rank distillation, with inference-side candidate constraints and prefix-aware decoding. Extensive experiments on CoSQA and ProCQA benchmarks demonstrate that CodeHID outperforms existing sparse retrieval, pre-trained code models, dense code retrieval, and generative retrieval baselines by a large margin in most cases, achieving particularly strong improvements in rank-one retrieval metrics.

cs.IR

版本更新 · v3arXiv:2608.00023

Role Steering of Language Models for Social Simulations

Isaac Song, Mohammed Rehan Parwani, Glenn Matlin, Emile Anand, Akhil Theerthala, Arjun Chatterjee, Anthony Wen-Ming Zang, Maria Kostylew 等 11 位作者

原文摘要

Social simulations built from language-model agents need role-conditioned behavior that can be checked before agents are placed into a simulated population. We introduce an activation-steering screening workflow for role-conditioned agents: define a role profile, extract a role-specific direction, sweep four steering coefficients, evaluate role-profile alignment, and pass or flag each candidate configuration. On OLMo-3-7B-Instruct, we apply the workflow to a mixed 275-role inventory with 228 role-agnostic questions, GPT-4.1-mini prompted role references, and GPT-4.1-mini judges. We also introduce CastVectors, which receive higher judged role-profile alignment than an assistant-axis directional control from prior persona-vector work, with mean overall scores of 63.2 versus 41.1 across the tested grid. They also preserve high lexical diversity, while the control drops sharply at larger coefficients. The role-level screen is the main contribution: most roles improve as steering increases, but 38 roles decline across all six measured dimensions, showing why simulation builders should choose coefficients per role rather than deploy a uniform high-strength setting. Our code is available at https://github.com/HCAI-Lab-GT/casting-call-vectors, and the role vectors and evaluation data at https://huggingface.co/datasets/HCAI-Lab-GT/casting-call-vectors.

cs.CL · cs.AI

版本更新 · v2arXiv:2609.36686

Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition

Hada Melino Muhammad, Luan Pham, Laure Barrière, Sachin Shetty, Leonardo Pulga, Flora D. Salim

原文摘要

Identifying the root cause of an anomaly among hundreds of sensors is critical for preventing safety incidents and costly downtime in complex monitored systems. Existing studies evaluate root cause analysis (RCA) methods using top@k accuracy. We show that this metric has a fundamental blind spot: it conflates two failure modes, retrieval failure, where the true cause is never considered, and reranking failure, where it is considered but ranked too low. In this work, we introduce a retrieval-reranking decomposition and audit four well-known benchmarks to expose this blind spot. Our experiments show that, on industrial CPS benchmarks, the statistical baseline scoring every sensor mis-ranks the true cause 79-100% of the time, and graph-based methods never clearly beat the best statistical baseline, whether their causal graphs are learned on short fault windows, on retrieved candidate pools guaranteed to contain the cause, or on multi-day normal-operation data. Meanwhile, on microservice benchmarks, where each injected fault drives the faulty service's own metric far above its baseline, retrieval is nearly solved (98-100%). Guided by the decomposition, we build a two-stage pipeline combining a multi-signal retriever with an LLM reranker that, as one fixed configuration, matches or exceeds the best baseline's top@1 accuracy on all six benchmark suites (by up to +12 points), with no causal graph or labeled data required. When all methods rank the same retrieved candidates with the true cause guaranteed present, adding a short system-description document lets the reranker lead the best baseline by +7 to +18 points on every benchmark. Code is available at https://github.com/cruiseresearchgroup/DecompRCA.

cs.LG