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

+1112新增论文
+875其中 AI 相关
+133已有论文修订
+96新增 AI 导读

arXiv 最近完成扫描:2026-11-19 23:27 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 00:23 — 2026-11-20 00:23(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:2026-11-19 23:27最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 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 20,663 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 23:25(北京时间)
新论文 · v1arXiv:2611.20993

Digits in Notation Are Not Numbers: A Scoring Pitfall in PDF-to-Markdown Conversion of Japanese Technical Documents (Preliminary Evaluation)

Mitsumasa Wada

原文摘要

Converting PDFs to Markdown is now routine preprocessing for search and language models, yet scoring the numbers in the output is easy to get wrong. We evaluate MinerU, a plain-text OCR baseline (NDLOCR-Lite), and a deterministic post-processing pipeline (anchor insertion, footnote reordering, fixes of look-alike characters in fixed contexts, gated formula repair using two independent OCR partners, and heading reconstruction) on 48 public Japanese pages (three documents), text-layer and rasterized. Our pre-specified number-and-unit F1 favored the OCR baseline (0.575 vs 0.397), and a disagreement check between the two engines seemed to flag about half of the converter's number errors (54.6%). Both were artifacts. The scorer counted digits in the converter's notation (image-link paths, HTML attributes), which plain text lacks. With the notation removed (a post-hoc check), the F1 scores tie (0.575 vs 0.594), and the check flags only 13% of number errors, because most errors are misses that both engines share. What remains: the OCR baseline has a lower body character error rate (0.012 vs 0.053 rasterized). The pipeline raises extra-number recall at page level (+0.145; the document-level interval touches 0), mostly by restoring page numbers, but lowers heading-level agreement (0.133 to 0.061) and leaves spurious formulas unchanged; its formula repair never fires. A pre-specified precision gate for its flags (0.80, human-judged) is met at 0.929, yet the post-processing hypothesis fails on its improvement items. We recommend scoring numbers after removing notation and checking critical figures against the source. By the pre-specified criteria, the study stays a technical report.

cs.CV

新论文 · v1arXiv:2611.20992

MedJev: A System One Vision-Language Decision Model for Fast and Effective Medical Image Understanding

Fan Zhang, Hao Wu, Jinyang Wu, Hongyu Qu, Zheng Lian, Dongfu Yin, Qingsong Wen, Pheng-Ann Heng

原文摘要

Medical image understanding with vision-language models (VLMs) typically relies on autoregressively generating reasoning and answer tokens. These unnecessary tokens make the inference cost scale with the response length and force the answer to be parsed from free-form text, incurring avoidable latency and decision errors. To this end, we introduce \textsc{MedJev}, a \emph{system one} vision-language decision model that maps medical images, questions, and candidate answers directly to decisions in a single multimodal forward pass, without any autoregressive generation process. For fast inference, \textsc{MedJev} removes the upper language layers and the generative output pathway, while keeping the full vision pathway and all visual tokens. On this shortened backbone, a decision head scores each candidate by pretrained query--key matching and refines the scores with a lightweight multilayer perceptron (MLP) residual, coupling the pretrained matching structure with task-specific nonlinear discrimination. Built on Qwen3.5-4B, \textsc{MedJev}-4B improves both accuracy and speed over the original model on each of four medical image classification and visual question answering benchmarks, with an absolute accuracy gain of \textbf{7.93\%} and a \textbf{6.04$\times$} end-to-end speedup. Further comparison with 20 cutting-edge models shows that \textsc{MedJev}-4B achieves state-of-the-art performance and inference speed among 4B--9B general and medical VLMs, indicating that direct multimodal decision making is an effective route to fast and effective medical image understanding.

cs.CV

新论文 · v1arXiv:2611.20991

FH-Sampling: Frequency-aware Hypergraph-driven Oversampling for Imbalanced Time-Series Classification

Yunrong Hao, Ruohao Dai, Zhen Liu, Guan Wang, Wenbin Pei, Qiang Zhang

原文摘要

Imbalanced time-series data appears commonly in diverse applications, such as medical diagnosis. When trained on imbalanced data, classifiers tend to exhibit a bias toward the majority class, making it difficult to identify minority-class instances accurately, despite their critical importance. Sampling techniques have proven effective in rebalancing imbalanced data. However, existing interpolation-based oversampling methods typically rely on pairwise interpolation, limiting their ability to capture high-order inter-sample relationships, and their inherent smoothing effects tend to suppress high-frequency components, compromising spectral fidelity. Therefore, we propose a Frequency-aware Hypergraph-driven Oversampling method (FH-Sampling) for imbalanced time-series classification. In FH-Sampling, a hypergraph is first constructed in the original time-series space to capture complex high-order inter-sample relationships, and sampling ratios are adaptively assigned to mitigate the impact of noisy samples. The discrete wavelet transform decomposes each sample into frequency components. Guided by the sample hypergraph, FH-Sampling combines high-frequency components from related samples while retaining the target sample's low-frequency component to help preserve important frequency characteristics. Experiments on 24 imbalanced datasets demonstrate the advantages of FH-Sampling for imbalanced time-series classification. We further apply FH-Sampling to aircraft trajectory generation. Experiments on simulated aircraft trajectories show that FH-Sampling produces trajectories that better match the real distribution, highlighting its potential for practical applications.

cs.LG

新论文 · v1arXiv:2611.20988

Hivemind: A Federated Protocol for AI-Mediated Tacit Knowledge Sharing in Organisations

Srinivasan Sundaresan

原文摘要

This paper presents Hivemind, a federated protocol that enables AI agents to exchange tacit knowledge on behalf of their users, asynchronously and without requiring any direct human interaction. Individual AI memory systems capture the decisions, reasoning, and contextual knowledge that surface during AI-assisted work. Hivemind creates the shared space in which this captured knowledge can flow between individuals across team and departmental boundaries, addressing a structural gap that neither centralised knowledge repositories nor existing AI tooling closes, even where partial solutions such as expert-finding systems exist. The paper evaluates centralised versus decentralised design approaches, proposes a federated architecture grounded in Nonaka and Takeuchi's (1995) Socialisation, Externalisation, Combination and Internalisation (SECI) model, and demonstrates a proof-of-concept implementation using Design Science Research (DSR) methodology. Measuring the enterprise benefit of federated tacit expertise sharing remains an open task for future work.

cs.AI · cs.MA

新论文 · v1arXiv:2611.20986

Calpha: Toward Native Biomolecular Intelligence in a General-Purpose Language Model

Yong Liu, Zhanpeng Shi, Peicong Lin, Zhenyi Zhong, Yizhou Dang, Wendi Wu, Haoling Li, Shuangjia Zheng

原文摘要

Biomolecular foundation models predict the structures of proteins and their complexes accurately, and large language models (LLMs) reason in natural language, but the two remain separate: the abilities of the former are not part of a general-purpose LLM, and the reasoning of the latter does not enter a structure prediction. Calpha aims at one general model that folds proteins and complexes, understands protein sequence and structure, and lets its language reasoning influence the structures it predicts. This report covers the first step, in which an LLM outputs single-chain protein structures. Qwen3.5-9B reads a sequence enriched with ESM2 residue features. It can respond in text or emit a token that invokes a pretrained SimpleFold structure head, which receives information about the protein only through Qwen's residue states. Under a fixed folding request, the head achieves mean TM-scores of 0.808 on the FoldBench-334 development set, 0.635 on CASP16 domains and 0.900 on a CAMEO-style PDB set. We compare these predictions with a baseline in which ESM2-3B encodes the sequence and a fine-tuned SimpleFold-3B head predicts the coordinates. The two systems also differ in trainable weights, training duration and crop length. For chains of 100--299 residues, all three paired confidence intervals include zero. At 300--600 residues, the mean differences are -0.044, -0.160 and -0.025, respectively. In a separate test, four English request types triggered folding on every evaluated example. Protein training reduced accuracy on a 350-item MMLU-Pro subset from 77.4% to 70.3%. An LLM can therefore output single-chain structures from its own states, with lower long-chain scores in the current comparisons and reduced accuracy on the evaluated MMLU-Pro subset. Complex prediction, structure understanding and the effect of language reasoning on the predicted coordinates remain future work.

q-bio.QM · cs.AI

新论文 · v1arXiv:2611.20983

GRACE: Parallel Best-of-N Multi-Agent Analysis of Closed-Form Questions over Dataframes with Guardrail Selection and Adaptive Retry

Fabio Picariello, Salvatore Cipolla, Susanna Bonura, Vito Morreale

原文摘要

LLM agents answer closed-form questions over a tabular dataframe by writing and executing Python, almost always as a single rollout: one interpretation, one script, one result, accepted without comparison. The few pipelines that produce several candidates reconcile them by answer-agreement voting, which needs a single comparable scalar and always returns one, even when every candidate is wrong. We present GRACE (Generative, Ranked, Adaptive Code Ensemble), a production-oriented pipeline that instead runs parallel best-of-N selection specialised to dataframe code. N agents run concurrently under a strict, machine-checkable output contract, diversified by persona hints, per-retry rotation, and a two-regime temperature schedule. Rather than vote, GRACE judges the executed artefacts: a pairwise tournament pre-filters the pool and a domain-specialised guardrail either selects the best candidate or, when none is defensible, rejects the whole pool and abstains with a diagnosis (an option voting structurally lacks), which in turn drives an adaptive retry with per-agent feedback. On InfiAgent-DABench (DAEval, M = 246), using Qwen3.6-35B-A3B as the backbone, GRACE raises answer match from 39% for a single-rollout baseline to 71% (+32 pp, 1.8x), recovering 53% of previously wrong answers. On the same DAEval task, the smaller dense Qwen3.5-9B lifts answer match from 38% to 63% (+25 pp, 1.7x). A controlled 3 x 3 study that sweeps the number of parallel agents against the retry budget finds, on the 35B backbone, the two levers largely substitutable: once either one is generous, the other adds little, identifying a cheap operating point for deployment. The same directional pattern replicates on the independent DataBench benchmark, again on the Qwen3.6-35B-A3B backbone, where answer match rises by 15 percentage points (from 70% to 85%) across 400 sampled questions.

cs.AI · cs.LG

新论文 · v1arXiv:2611.20981

Breaking feature collapse in self-supervised time series encoders

Özgün Turgut, Daniel Rueckert

原文摘要

General-purpose time series encoders promise a single backbone that generalises across tasks and domains; however, they currently do not scale. We trace this down to a critical point of failure: under the predominant masked data modelling supervision, the encoder's output tokens partially collapse. This is the natural consequence of supervising encoders only in the input space, which leaves no constraint against redundant token dimensions in the feature space. We introduce OTISv2, which suppresses the collapse by complementing the reconstruction objective in input space with two objectives in the feature space: a self-distillation loss against an exponential-moving-average teacher, and a KoLeo regulariser. Under matched training, the resulting encoder reduces the cosine similarity and lifts the effective rank of its output tokens relative to its predecessor, and it scales monotonically from 7.1 M to 116 M parameters where its predecessor declines. It matches or surpasses existing general-purpose time series encoders across 143 uni- and multi-variate datasets. To foster further research, we release our code and pre-trained weights.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.26430

Physiology-Aware Graph Attention for Early Ventricular Reentry Prediction

Ma{ë}lis Morier, Jairo Rodr{í}guez Padilla, Mihaela Pop, Patrick Gallinari, Maxime Sermesant

原文摘要

Sudden cardiac death mostly originates from post-infarct ventricular tachycardia. This reentry is sustained by propagation around scar tissue, but its risk remains difficult to predict from infarct imaging alone. While in silico induction studies can reveal these mechanisms, exploring many substrates and pacing locations remains computationally expensive. We propose a graph attention classifier for early prediction of sustained ventricular reentry from simulated cardiac electrophysiology. Each simulation is represented as a graph with early nodal voltage samples and edge attributes encoding geometry, stimulation frequency, tissue labels, amplitude, and diastolic interval. These descriptors are computed only from the first two paced activations, before sustained reentry is observed. On a balanced independent test set of 1000 simulations, the classifier achieves 94.6% accuracy, 95.4% sensitivity, 93.8% specificity, 94.6% F1-score, 0.987 ROC-AUC, and 0.985 PR-AUC. Ablation experiments show that diastolic interval is the most critical descriptor. Qualitative attention inspection suggests that different heads focus on border-zone, stimulation location, and early propagation path. These results support graph attention as a fast early-prediction approach for large-scale in silico ventricular reentry studies.

cs.AI

新论文 · v1arXiv:2611.20980

Copying along Arithmetic Progressions Cannot Simulate Interleaving with Polylogarithmic Loss

Matthias G. Mayer

原文摘要

Two classical ways to compress a word are straight-line programs (SLPs), which build it by concatenating smaller pieces, and the Lempel-Ziv 77 (LZ77) factorisation, which copies earlier parts of it; their sizes are measures of repetitiveness. LZ77 approximates the smallest SLP efficiently: it has no more factors than a smallest SLP has size, and yields an SLP at most a logarithmic factor larger in near-linear time. Motivated by online prediction, Kosoy introduced zipline programs, which are analogous to SLPs but interleave their pieces round-robin instead of concatenating them. Her generalisation of LZ77, the arithmetic repetition system, describes a word by copies from one arithmetic progression of positions to a later one. Do arithmetic repetition systems approximate the smallest zipline program as well? Kosoy proved that the least size $\mathrm{ARC}(x)$ of an arithmetic repetition system for a word $x$ of length $n$ is at most a factor $O(n^{1/3})$ larger than the least size $\mathrm{ZLC}(x)$ of a zipline program for it, and asked whether this factor is tight. Her polynomial-time next-letter predictor makes $O(\mathrm{ARC}(x)\log n)$ mistakes, so a polylogarithmic factor would bound its mistakes by $\mathrm{ZLC}(x)\,\mathrm{polylog}(n)$, which no known polynomial-time predictor achieves. We show that the optimal exponent is $1/4$, not $1/3$: $\mathrm{ARC}(x) \le 2n^{1/4}\,\mathrm{ZLC}(x)$ for every word $x$, and at every large enough length $n$ some binary word has $\mathrm{ARC}(x) \ge n^{1/4-o(1)}\,\mathrm{ZLC}(x)$.

cs.DS · cs.FL

版本更新 · v2arXiv:2606.18788

HandwritingAgent: Language-Driven Handwriting Synthesis in Scalable Vector Space

Jaward Sesay, Yue Yu, Börje F. Karlsson

原文摘要

Teaching machines to emulate natural handwriting styles remains an open challenge, as it requires synthesizing stroke sequences that dynamically vary in shape, texture, pressure and script - not only across individuals, but also within a single person's handwriting. Attempts at this challenge have largely explored deep learning methods in both online and offline settings. However, these approaches are often constrained by style-specific architectural choices, heavy reliance on large datasets, high compute costs, and a lack of flexible control over writing styles through natural language. To this end, we introduce HandwritingAgent, a language-driven agent that can synthesize natural handwriting sequences directly in Scalable Vector Graphics (SVG) format with no need for style-specific training. The agent leverages a large reasoning model to geometrically analyse and autoregressively generate target handwritten glyphs as stroke sequences in a discrete grid canvas environment. Generation is conditioned on texts provided in either conversational or non-conversational mode, along with a reference handwriting-style image. Experiments on diverse handwriting tasks spanning imitation, recognition, multi-lingual handwriting synthesis, and generation of complex handwritten maths and science expressions indicate substantial improvement in performance, with HandwritingAgent matching or surpassing state-of-the-art generative handwriting models, while providing a more efficient, controllable, and generalizable synthesis method.

cs.CV · cs.CL

新论文 · v1arXiv:2611.20979

Adaptive-Elbow Graph Traversal for Schema Retrieval in Text-to-SQL

Fabio Picariello, Salvatore Cipolla, Susanna Bonura, Vito Morreale

原文摘要

LLM-based natural-language interfaces to relational databases are gated by a schema-retrieval step: the generator can only be as good as the slice of schema it is shown. On a database with hundreds of tables, that slice must be selected and the selection is two-sided---omit a needed table and the query becomes unrecoverable, include too many and the irrelevant ones act as noise that degrades the model's output. When an agentic retriever that lets the model inspect the schema can be too costly or too slow, the fallback is an embedder that ranks tables by cosine similarity and keeps a top-k. This fallback has two weaknesses: a fixed budget is suboptimal question by question, and embedding similarity overlooks foreign-key-linked tables that are necessary for joins. We present Adaptive-Elbow Graph Traversal (AEGT, ElbowHop for short), a property-graph table retriever that addresses both: an adaptive elbow cutoff replaces the fixed budget with a per-question one under a single aggressiveness parameter, and bidirectional foreign-key traversal deterministically recovers the bridge tables embedding similarity misses. We evaluate the retriever on 3 corpora of increasing candidate-pool size (BIRD Mini-Dev queried per database, 3--13 tables; its eleven schemas merged, 74; and a merged Spider-train graph, 546) and isolate the two mechanisms under a per-question budget-matched protocol. Across these settings the adaptive elbow emerges as the dominant mechanism---at matched recall it roughly doubles precision over a fixed budget on the larger pools, the margin widening as the pool grows---while the foreign-key traversal pays off on the join-critical bridge tables dense retrieval cannot reach, in the single-hop tight-budget case. We characterize the method as a low-cost, recall-robust first stage for schema retrieval on which a downstream selection or generation step can build.

cs.DB · cs.IR

新论文 · v1arXiv:2611.20975

STORMGUIDE-FL: Stochastic Remote Guidance for Efficient Mining of Federated Streaming Data

Manuel Röder, Frank-Michael Schleif

原文摘要

Federated Learning enables collaborative model training across distributed edge devices ("clients") while preserving data privacy. However, real-world deployments involve clients that observe continuous data streams from evolving environments while operating under strict resource limitations. Existing solutions still face two major challenges: local concept drift, where each client's data distribution shifts over time, and global client drift, arising from asynchronous engagement and imbalanced contributions across heterogeneous training participants, formally described as dual client heterogeneity. We propose STORMGUIDE-FL, a federated optimization and data-mining framework that mitigates both types of drift using a server-guided pipeline for data acquisition and local training. For data acquisition, a lightweight client-side sampling strategy incrementally selects informative and diverse instances from non-stationary, non-IID local streams under bounded memory, compute, and labeling budget. For local training, the server's remote guidance is embedded directly into local optimization as an update-level correction, counteracting client drift without discarding scarce labeled samples. We empirically verify the effectiveness of the proposed sampling strategy on federated data streams across gradual, sudden, and recurring concept drift, and demonstrate that its gains compound with the update-level drift correction. Experimental results further show improved speed and robustness of global model convergence under resource-constrained, heterogeneous conditions.

cs.LG · cs.DB · cs.DC

新论文 · v1arXiv:2611.20972

FARCH: A Functional ARCH Model for Calibrated Prediction Bands

Mohamed Chaouch

原文摘要

Forecasting a curve, rather than a handful of scalar summaries of it, requires a notion of uncertainty that is itself functional. We propose FARCH, a functional nonlinear autoregressive model with conditional heteroscedasticity, in which the conditional mean and the conditional volatility of the next curve are forecasted jointly and nonparametrically, by reusing a single kernel weighting scheme --- built on a wavelet semi-metric between curves --- first on the curves themselves and then on their squared residuals. From this pair of estimators we derive two constructions of prediction bands: a pointwise band, obtained from marginal scenario quantiles, and a uniform, sup-norm band, calibrated for decisions that concern the entire forecasted path rather than any single instant. Applied to day-ahead forecasting of half-hourly French national electricity demand (1996--2009), and compared, under an identical protocol, against four existing prediction-interval constructions that do not model the conditional variance explicitly, the uniform FARCH band attains pointwise coverage statistically indistinguishable from its nominal target at the 80%, 90% and 95% levels, and a curve-wise coverage of 90.1%, significantly above the 70.8% reached by the best competing method, at the cost of a wider interval. Pointwise bands, in contrast, undercover regardless of whether the variance is modelled explicitly, indicating that state-dependent volatility and simultaneous calibration are two distinct ingredients that a trustworthy prediction band must combine.

stat.ME · cs.LG · stat.ML

新论文 · v1arXiv:2611.20970

Hilbert States for Decision-Making under Partial Observability

Zibo Meng, Andrew C. M. Austin, Alin Achim

原文摘要

Decision-making under partial observability can be fundamentally limited by information, even with known dynamics: distinct physical states can induce the same observation history while favoring different actions. We study three questions: when is full-state optimality unattainable, what information exactly preserves the best observation-based decision, and how does finite-data learning affect reliability? First, we characterize decision ambiguity through conditional action preferences. We give a zero-regret criterion, a positive lower bound for conflicting uniquely optimal actions on positive-probability regions with uniformly positive cost gaps, and an exact binary-action regret formula. This also shows why physical-state ambiguity alone need not cause decision loss. Second, for two actions and squared terminal-goal costs in the plane, we derive an exact inner-product representation of conditional expected cost differences using three conditional moment contrasts and a goal-dependent feature. This Hilbert state preserves observation-optimal actions without hidden-state reconstruction. Under nondegenerate history and goal variation, its three-dimensional form is minimal among exact bilinear cost-contrast representations. Third, we relate finite-data state errors to excess decision regret via goal-projected errors, action margins, and goal geometry. Physics-based simulations verify information-limited regret, exact action preservation, and the role of second moments. Held-out real-SAR experiments demonstrate feasible goal-conditioned decisions from masked images, while finite-data evaluations reveal goal-dependent reliability. Together, these results separate irreducible information loss, exact representation sufficiency, and learning-induced excess regret.

cs.AI · cs.LG

新论文 · v1arXiv:2611.20969

AutoDiDact: Input Reduction over Inferred Structure

Aarush Kumbhakern, Rahul Gopinath

原文摘要

Delta debugging reduces a failing input by deleting chunks of it, keeping a deletion only if an oracle confirms the failure persists. It chunks the input based only on its length, so its deletions cut through units such as identifiers and delimited groups, wasting calls and leaving outputs large. Current state-of-the-art structural reducers avoid this by supplying grammars or built-in format knowledge. We show that structured reduction needs neither: a neutral word and delimiter pairs suffice, and both can be inferred from the failing input by asking only what delta debugging already asks its oracle: does the failure persist? A neutral word, such as a space, preserves the failure when inserted between such units but not inside them, so it splits the input into tokens. A delimiter pair is two tokens that preserve the failure only when added or removed together, so the span they bound can be reduced as a unit. We formalize both, state when the oracle can reveal them, and learn each with a bounded number of calls. AutoDiDact reduces the resulting tree of spans by hierarchical delta debugging (HDD) and shrinks each token across its occurrences. AutoDiDact finds a neutral word in 75 of 125 inputs from 18 format families. On these, it returns outputs 83% smaller than byte-level delta debugging with 37% fewer calls on geometric mean, inference included. The savings grow with input size, to 98% and 87% on inputs of at least 10 KiB. Without a grammar, AutoDiDact matches grammar-based HDD in output size at 3.85 times its calls, and uses 54% fewer calls than C-Reduce's language-agnostic mode. Because it needs only the oracle, AutoDiDact can minimize whatever a fuzzer finds, malformed inputs included.

cs.SE

版本更新 · v2arXiv:2608.30468

Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering

Jueun Kim, Sungho Park, Wook-Shin Han

原文摘要

A central bottleneck in multi-hop Question Answering (QA) is that the granularity at which a question is expressed often differs from the granularity at which corpus evidence is retrievable. Existing methods address this mismatch by imposing fixed graph structures over the corpus, by iteratively reformulating the query, or by executing a generated program over it, but these strategies do not explicitly decide when a query unit is already supported by evidence and when it should be refined. We formulate this bottleneck as retrievable granularity discovery and introduce Hi-Q, an evidence-conditioned framework for hierarchical query refinement. At each query node, a resolution operator tests whether retrieved evidence supports the current query unit; resolved nodes terminate, while unresolved nodes are expanded by a dependency-preserving binary operator and checked by a semantic coverage verifier. Hi-Q therefore grows a query tree whose topology is determined by corpus support signals rather than by a fixed decomposition template or a pre-built graph. We evaluate Hi-Q on three multi-hop QA benchmarks, primarily under full-corpus retrieval, where dependent evidence must be located among open-domain distractors rather than within a small annotated pool. In this setting Hi-Q reaches 52.3 EM and 64.0 F1 averaged over the three benchmarks, ahead of the iterative retrieval baseline IRCoT by 15.1 EM / 18.2 F1 on that same average, and ahead of the graph-based RAG baseline PropRAG by 11.5 EM / 12.0 F1 on MuSiQue-full, without corpus-wide graph construction. In the restricted supporting/distractor setting used by prior work, Hi-Q likewise attains the best accuracy, with 57.9 EM and 69.3 F1 on average, ahead of PropRAG by 5.6 EM / 3.9 F1 and IRCoT by 13.7 EM / 15.8 F1. The project page is available at https://hi-q-project.github.io/.

cs.CL · cs.IR

版本更新 · v3arXiv:2607.26817

From Uncertainty to Determinism: Coarse-to-Fine Visual Floorplan Localization without Ray Matching

Shiyong Meng, Bolei Chen, Ping Zhong, Yang Wan, Rongzhi Wang, Jiazhi Xia, Jianxin Wang

原文摘要

Visual Floorplan Localization (FLoc) has emerged as a promising solution for indoor localization by matching egocentric images against minimalist structural maps. However, due to cross-modal information asymmetry and repetitive indoor layouts, visual FLoc is fundamentally challenged by multimodal pose distributions, where visually identical observations map to distinct, spatially separated locations. Existing ray-matching-based methods tackle this by explicitly predicting sparse geometric or semantic rays, which inherently incur information loss and demand resource-intensive preprocessing alongside exhaustive matching during inference. In this paper, we bypass the intermediate ray-matching paradigm and propose a coarse-to-fine visual FLoc framework that progresses from uncertainty to determinism. In the coarse stage, we design an image-conditioned pose diffusion model to parameterize the continuous multimodal pose distribution, effectively routing stochastically initialized pose particles toward distinct candidate modes. In the refinement stage, we propose a localized refiner that predicts bounded sub-meter pose residuals from candidate-centered floorplan crops, where structural ambiguities are largely eliminated. Our method effectively balances global multi-hypothesis tracking and local sub-meter refinement without requiring any offline map preprocessing or test-time lookup tables. Comprehensive results on the S3D (full) and ZInD benchmarks demonstrate that our approach achieves state-of-the-art accuracy and robustness.

cs.RO · cs.CV

新论文 · v1arXiv:2611.20955

Jev-as-a-Reward: Validating Probabilistic Safety Judges for Reinforcement Learning

Eunkyeong Lee, Junhyung Moon, Seunggwan Hong, Dongsuk Oh

原文摘要

Probabilistic safety judges return the probability of a safety label and cheaply score reinforcement learning rollouts. A confidence gate sends only uncertain verdicts to a stronger LLM judge, which leaves confidently passed harm in a blind spot. Policies can exploit this blind spot, and commercial judges release new versions. We propose a protocol that validates such a judge before and during training, separates the share of confidently passed harm from its amount, and re-validates it after each judge change. We apply it to two versions of Jev, a commercial decision-only judge, and to an open guard classifier. Under the probability reward of Jev, passed harm shrinks in all 11 runs under the primary reference, mostly more slowly than caught harm, and concentrates in the blind spot. Binarizing this judge meets the escape criterion on Llama, and the open guard classifier shows an escape signal in one seed under a second reference. Guard classifiers share this blind spot, and even frontier LLM judges catch at most one of 10 human-labeled confident misses. Without a trained reward model, the probability reward with a helpfulness term lowers HarmBench attack success on Llama-3.1-8B from 0.287 to at most 0.033 at the final checkpoint.

cs.AI · cs.CL

新论文 · v1arXiv:2611.20953

Same Fix, Different Weights: Replicating Weight-Space Programming with Claude

Subham Kundu

原文摘要

Takehi et al. (2026) report that GPT-6 Astra, given the weights of small neural networks as text, can say what they were trained to do, repair them, and write new ones without training. I re-ran the core of that study with Claude Opus 5.5 in ten pre-registered experiments, with untrained-network and permutation controls and hand audits of every sandboxed code cell. Reading was mixed: Claude named 3 of 4 Atari games from policy weights and found the measured copying heads in 15/15 character-LM runs, but its answers about training data often followed priors. Unlike the original, it identified a sycophantic Gemma 3 270M finetune from weights alone in 6/6 runs. One-shot weight edits took a failing MountainCar policy from 0% to 100% success and a hovering LunarLander policy from 0% to 85.6%; zero-shot networks beat PPO at 100k steps on 4 of 5 environments, each implementing a textbook controller. With no training or forward passes, Claude wrote a 1.48M-parameter 9x9 Go network that won 85-94% of games against three PPO opponents. Given Qwen3.5-0.8B's weights and 10, 25 or 50 forward passes of 64 practice problems, Claude raised MATH-500 from 6.7% to 51.4%, 55.2% and 58.1% (+51.4 points at 50 passes, 95% CI [47.9, 55.0]; original 48.1%), GSM8K from 11.6% to 68.2% and IFEval from 22.2% to 54.2%. Unlike the original, which removed an internal loop direction, every edit acted at the output: it scaled the final norm, raising the effective sampling temperature, and lowered the logit of "Wait" while raising that of </think>. The norm scaling alone reaches only 20.9-22.1% on MATH-500. On Gemma 3 270M, which rarely loops, no edit helped (-0.8 points), as in the original.

cs.LG

版本更新 · v2arXiv:2609.12892

Beyond Accuracy: Uncertainty-Guided Boundary Refinement for Reliable Biomedical Image Segmentation

Anima Kujur

原文摘要

Accurate biomedical image segmentation requires not only high global overlap but also reliable delineation of clinically meaningful boundaries. In blood-smear microscopy, cytoplasm and nucleus contours provide the structural basis for downstream morphology analysis; however, deep segmentation models may remain uncertain or overconfident near ambiguous boundary regions even when achieving strong Dice scores. This work proposes a Reliability-Aware Boundary Refinement Network (RABR-Net), a two-stage framework for reliability-aware biomedical image segmentation. A strong UNet++ EfficientNet-B4 base segmenter first produces initial class probabilities and logits. Predictive entropy, test-time augmentation variance, margin uncertainty, foreground probability gradients, and foreground soft-boundary cues are combined with the multiclass probabilities into a reliability-aware representation. This representation guides a gated residual refiner that selectively corrects uncertain boundary regions while preserving confident regions of the base prediction. The framework is evaluated using overlap accuracy, class-wise Dice, Boundary Dice, HD95/ASSD, expected calibration error, risk-coverage analysis, qualitative correction maps, and paired statistical testing. As a separate diagnostic analysis, we additionally characterize the sensitivity of the selected base segmenter to deterministic microscopy image perturbations.

cs.CV · cs.LG

新论文 · v1arXiv:2611.20950

ROSE: A Shared Cross-Embodiment Facial-Motion Latent Space for Humanoid Robot Expression

Yongji Fu, Man Cao, Yi Zhou, Fei Lin, Mark F. Hansen, Guanqun Cao

原文摘要

Natural, coherent full-face dynamic expressions are central to making humanoid robots socially approachable, yet existing systems commonly realize only limited lip motion or scripted expressions. The limitation is both physical and algorithmic. A compact head leaves little room for densely packed, independently controllable actuation; meanwhile, learned systems often generate an avatar video, landmarks, or facial parameters and then infer actuator commands through visual retargeting. This render-and-invert path adds latency and artifacts, and it does not reliably transfer generated behavior to a physical robot. We present ROSE (RObot facial expression through Shared motion Embeddings), a framework that integrates biomimetic hardware, cross-embodiment motion representation learning, and multimodal motion generation. On the hardware side, we build a flexible tendon-sheath transmission structure that integrates 34 actuators into a 19.5 cm biomimetic head. By decoupling actuator placement from facial action points, it enables coordinated full-face expression within a compact volume. On the algorithmic side, ROSE-VAE learns an identity-independent shared facial-motion latent space from human, digital-human, and robot observations. ROSE-Flow directly maps text, audio, or their combination to trajectories in this motion space without using video as a generator input. ROSE-ACT then converts these trajectories into constrained actuator commands. Our system demonstrates how high-density biomimetic hardware and a shared executable facial-motion representation can jointly unify cross-embodiment learning, multimodal generation, and physical robot expression.

cs.RO

新论文 · v1arXiv:2611.20948

One Code per Material: Neural Representation and Generation of Measured BTFs

Fazilet Gokbudak, Canberk Baykal, Chenliang Zhou, Rafal Mantiuk, Cengiz Oztireli

原文摘要

Measured bidirectional texture functions (BTFs) capture the full appearance of real materials--including parallax, self-shadowing and inter-reflections that analytic SVBRDFs cannot express--but each measurement is billions of values, and every new material requires a new capture. Existing neural BTF representations encode each material as large per-texel latent maps rather than as a point in a shared space from which new materials could be sampled. We present neural representations of measured BTFs at two operating points. A per-material coordinate network outperforms the recent neural BTF of Xia et al. at matched size (+3.2 dB PSNR) and all prior baselines on every metric. A compact model represents each material by a single 256-dimensional code that conditions a shared decoder; it exceeds the PSNR (+1.2 dB) and colour accuracy of the per-texel latent maps of Rainer et al. with 256 numbers per material instead of millions, and one decoder shared by all materials. Because each material is a single point in this code space, measured BTFs can be sampled: a class-conditional flow over the codes, trained on the 84 materials enlarged with colourways and hue rotations, generates materials that render and relight as full BTFs.

cs.GR

版本更新 · v2arXiv:2609.07151

Vishing-Tactics-Bench: Forecasting Exploitation Trajectories in Voice Phishing Calls

Jeongmin Lee, Dongmyung Sul, Seung Yun, Jinxia Huang

原文摘要

Voice phishing (vishing) unfolds in real time; by the time a call has ended and post-hoc classification is possible, the harm has already been done. The more actionable question is which concrete harm (Information Gathering or Financial Exploitation) an ongoing call is tactically progressing toward. We present Vishing-Tactics-Bench, a benchmark grounded in Endsley's situation-awareness (SA) framework that recasts vishing defense from after-the-fact fraud classification to harm projection: predicting at each turn whether the call will reach either terminal harm. We adapt MITRE ATT&CK to vishing as a 6-tactic taxonomy (Vishing-Tactics) and label 35,340 scammer utterances across 5,645 synthetic Chinese calls. We define Exploitation Trajectory Forecasting, a survival-style protocol over the two terminal harms with three metrics: AP@k, C-index, and divergence error. Baselines ranging from a Markov heuristic to fine-tuned LLMs show that the tactical trajectory serves as an interpretable representation of the call's tactical state, supporting harm-specific forecasting, which can then be used for the downstream application of intervention selection; a stratified lead-time analysis at a tight false-alarm budget further identifies at what point in a call the trajectory signal yields early warning.

cs.CL

版本更新 · v2arXiv:2611.02376

High-Throughput Private Information Retrieval with on-CPU Accelerators

Gyuyeong Kim

原文摘要

We present AltoPIR, the first PIR system that exploits the capability of emerging on-CPU matrix accelerators such as Intel AMX. Unlike existing solutions, AltoPIR achieves high-performance PIR through efficient batching without requiring discrete accelerators. However, the on-CPU accelerator has only a few small registers and shares its core with request handling. As a result, it runs far below its peak rate while its operands arrive from memory, and it remains idle while its core handles requests. To keep the accelerator busy, we design mechanisms that reduce both the memory traffic of a batch and the core cycles spent on each request. Our experimental results show that AltoPIR outperforms existing CPU-based solutions by up to 50.1x.

cs.OS · cs.CR · cs.DB

新论文 · v1arXiv:2611.20943

From Strong Normalization to WhatsApp: the Journey of an Axiom

Giuseppe Castagna

原文摘要

Twenty years ago, Mariangiola Dezani-Ciancaglini, Daniele Varacca and I showed that Milner's classic encoding of functions into processes does not respect one of the laws of intersection types, the one stating that $(σ\toτ)\land(σ\toρ)$ is a subtype of $σ\to(τ\landρ)$, which Barendregt, Coppo and Dezani-Ciancaglini had stated in 1983 for their filter $λ$-model. In this essay I show that this observation is the key to closing what a colleague at Meta calls ``the main typing gap in Erlang''---the language in which the servers of WhatsApp are written: the type of the function that implements a server is not related to the type of the server, so that a client may expect from the server a reply that the server will never send. Actually, closing this gap is just an excuse to follow the journey of the law above, and of some of its relatives, from the study of strong normalization in the $λ$-calculus to the type systems of Elixir and Erlang: a journey that shows how much the practical typing of these languages owes to the work of Mario Coppo, Mariangiola Dezani-Ciancaglini and Simona Ronchi Della Rocca, to whom this essay is dedicated for their eightieth birthdays.

cs.PL · cs.LO

新论文 · v1arXiv:2611.20939

TacBridge: Learning Unified Tactile Representations through Cross-Sensor Correspondence

Yongji Fu, Yijiong Lin, Yi Zhou, Yi Qi, Guanqun Cao

原文摘要

Optical tactile sensors record tactile videos that capture local deformation and its temporal evolution during contact, supporting robot manipulation, force estimation, and tactile representation learning. Differences in imaging geometry, background appearance, illumination, resolution, and deformation response lead to sensor-dependent observations of the same contact across GelSight, DIGIT, GelSlim, TacTip, and other optical tactile sensors. This variability limits representation transfer and the joint use of multi-sensor data. We introduce TacBridge, a framework for learning unified representations from multi-sensor tactile videos through cross-sensor correspondence. Specifically, multi-sensor masked tactile-video pre-training learns spatiotemporal representations across sensors. We then train the same masked model jointly on same-sensor and cross-sensor reconstruction, using paired source and target videos of matched contact events. Experiments on cross-sensor translation and downstream perception demonstrate the cross-sensor generalization and task transferability of the learned tactile representations.

cs.RO

版本更新 · v2arXiv:2611.16493

ReA-Bench: Benchmarking Responsible Agent Auditing

Zipeng Ye, Shenyu Dai, Yong Xie, Kun Wang, Jiyang Guan, Zhikai Chen, Jiaqi Weng, Jialing Tao 等 9 位作者

原文摘要

As agents perform tasks autonomously in local and cloud environments, auditing their execution trajectories can help service providers identify risks and improve agent harnesses and foundation models. Our analysis of production and red-team trajectories shows that some risks are repeatedly missed across auditing configurations. Overall recall obscures which risks are missed and whether higher recall comes with more false positives on legitimate behavior. Existing benchmarks offer limited insight into these failures. Generated trajectories can contain inconsistent tool calls and responses, conspicuous risky actions, or repetitive attack patterns. Grouping results by risk type also makes it difficult to tell whether auditors overlooked evidence, accepted an unsupported conclusion, or lacked information needed to make a judgment. We introduce ReA-Bench, a diagnostic benchmark for auditing responsible agent behavior. It organizes auditing challenges into six tiers: internal safety knowledge, contradictions within trajectories, evidence retrieval in long contexts, verification of sources and reasoning, indirect steering, and missing information. It includes challenging benign cases in which actions resemble risky ones but are consistent with the task and its authorization. It also provides paired trajectory versions to test whether auditors detect the same risks more reliably when the trajectory is shortened or missing information is supplied. Most samples are drawn from real production trajectories, with scenarios manually selected and adapted to preserve realistic tasks and risks that could plausibly arise during execution.

cs.AI

新论文 · v1arXiv:2611.20937

Learning What the True Labels Would Teach: Posterior Analytic Class-Incremental Learning with Unlabeled Data

Wei Tang, Tong Wei, Jiahao Zhang, Min-Ling Zhang, Lijie Hu, Fakhri Karray

原文摘要

In class-incremental learning with unlabeled data, each task brings only class names and unlabeled images, so CLIP's zero-shot predictions replace labels. Existing methods train on hard pseudo-labels, but a wrong one gives the true class zero probability, which self-training often confirms. We argue that each image should carry its label posterior, as an analytic classifier trained on posteriors equals the true-label one in expectation. The zero-shot prediction is not this posterior, as its class proportions confound name bias with true imbalance and it ignores other images. We propose Posterior Analytic Class-Incremental Learning (PACIL), which corrects the class prior with a prior selection rule and refines each distribution by a fixed-prior von Mises-Fisher mixture on whitened features. These soft labels train the classifier and replace labels to select its fusion weight with zero-shot CLIP by closed-form leave-one-out cross-validation. We prove that posterior targets minimize the mean-square gap to the true-label prediction and that their argmax widens this gap only through ambiguous images. The fusion weight selected with soft labels loses at most their distance to the posteriors in expected correct decisions. PACIL has the best average incremental accuracy among methods trained without labels on all 18 settings.

cs.LG · cs.CV

新论文 · v1arXiv:2611.20936

ReAccess: Look Once, Stay Focused with Efficient Test Time Memory

Tianhao Chen, Yilong Fan, Yuheng Wu, Xiaobin Hu, Dongman Lee

原文摘要

Despite recent advances, vision-language models (VLMs) still struggle with fine-grained visual understanding, often failing to effectively utilize critical evidence already encoded in their visual representations. Existing approaches address this limitation through repeated visual processing or explicit reasoning, introducing substantial computational overhead. In this paper, we propose ReAccess, a lightweight framework that preserves and reuses question-relevant visual evidence through compact associative memory. Constructed during a single visual prefill, the memory supports progressive evidence retrieval that steers both attention queries and hidden representations, enabling effective visual grounding without repeated image encoding or explicit reasoning traces. Extensive experiments demonstrate consistent improvements in both general visual understanding and fine-grained perception, while achieving substantially faster inference than existing reasoning-intensive approaches, demonstrating a promising path to efficient multimodal reasoning.

cs.CV · cs.AI

版本更新 · v2arXiv:2605.21543

Provable Joint Decontamination for Benchmarking Multiple Large Language Models

Zhenlong Liu, Hao Zeng, Hongxin Wei

原文摘要

Benchmark data contamination has become a central challenge in LLM evaluation: when evaluation examples appear in the training data of one or more audited models, reported performance can be inflated and cross-model comparisons become unreliable. A broad line of training-data detection work designs scores to quantify how strongly a model memorizes a given data point, but these score-based methods lack theoretical guarantees. Recent conformal approaches provide provable false-identification control for a single model; however, applying them separately to each model can produce model-specific benchmarks, undermining fair comparison across models. In this work, we formalize multi-model benchmark decontamination as a joint selection problem and propose Joint Envelope Conformal Selection (JECS), a conformal procedure that enables global contamination rate (GCR) control under stated assumptions. Specifically, JECS computes per-model conformal p-values, aggregates them by the per-item maximum, and reconstructs a conservative envelope of the max-p null distribution from right-tail observations above a data-driven threshold. By applying the adaptive Benjamini-Hochberg (BH) procedure to the envelope-rescaled values, we select a benchmark with provable GCR control. Extensive experiments across various models and benchmarks demonstrate that JECS achieves higher power than the max-p baseline while consistently maintaining the target GCR control.

cs.LG