跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1171新增论文
+938其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 17:46各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 18:39 — 2026-11-19 18:39(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 06:59最近发现新增版本:2026-11-19 17:46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。

27,410 已收录论文22,788 AI 相关8,343 有修订112 HF 社区发现

论文修订列表

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 8,343 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v2arXiv:2608.19172

Cell-Probe Lower Bounds and Complexity-Preserving Reductions for Suffix Array Queries

Dominik Kempa, Tomasz Kociumaka

原文摘要

For a text $T$ of length $n$ over an alphabet of size $σ$, its suffix array lists the starting positions of the suffixes of $T$ in lexicographic order, and its inverse suffix array gives the lexicographic rank of the suffix starting at each position. Since the introduction of the FM-index and the compressed suffix array in 2000, both queries have been supported in $O((\log_σn)^ε)$ time using $O(n\logσ)$ bits, for any constant $ε>0$. Yet no nontrivial time-space lower bound for suffix-array queries in compact space was known. We give the first such lower bound: in the cell-probe model with $Θ(\log n)$-bit words, every deterministic $S$-bit data structure with $S\ge n$ answering suffix-array queries on binary strings of length at most $n$ has worst-case query time $Ω(\log\log n/\log((S/n)\log\log n))$. Hence, structures with $O(n(\log\log n)^{O(1)})$ bits need $Ω(\log\log n/\log\log\log n)$ query time, while constant query time requires $Ω(n\log^εn)$ bits for some constant $ε>0$, matching known upper bounds. In particular, no such $O(n)$-bit structure supports constant-time queries, answering the 25-year-old question of Grossi and Vitter. We also give exact complexity-preserving equivalences between suffix-array access and simpler prefix queries on short strings. For every $2\leqσ\leq n$, suffix-array queries are equivalent to prefix-select queries, and inverse-suffix-array queries are equivalent to prefix-special-rank queries. The reductions in both directions preserve all four standard measures up to constant factors: space, query time, preprocessing time, and preprocessing space. Unlike previous reductions, they incur no additive $O(\log\log n)$ query-time term. Thus, the corresponding prefix-query problems capture suffix-array and inverse-suffix-array access without asymptotic loss in any of the four measures.

cs.DS

版本更新 · v3arXiv:2606.00043

Fake Plastic Voters: When Political Parties Can Use AI-Simulated Focus Groups

Claudio Novelli, Javier Argota Sanchez-Vaquerizo, Jennifer Cyr, Giuliano Formisano, Simon McDougall, Giulia Sandri, Luciano Floridi

原文摘要

Political parties strive to understand their electorates, and focus groups are a vital tool in these efforts. AI-enhanced simulation technologies (AESTs) enable synthetic focus groups in a fraction of the time (and cost), raising the question of when and how such simulated evidence can be used in campaign research. This paper develops a decision matrix to help party strategists match research needs to appropriate simulation technologies and to identify when to escalate to hybrid or fully human focus groups. The matrix combines three dimensions: strategic purpose, deployment risk, and empirical grounding of the simulation tool. Strategic purpose is the decisive dimension, as it determines what kind of evidence the focus group is meant to produce: observing how political meanings and identities emerge through interaction (Mode 1) or testing and refining campaign messages (Mode 2). The matrix shows that, given documented failure modes such as sycophancy, persona drift, and the suppression of minority viewpoints, AESTs cannot replace human interaction in Mode 1 at any risk level. Within Mode 2, suitability depends instead on deployment risk and on the empirical grounding. Yet even here, we caution that routine reliance on AESTs may erode the qualitative craft on which sound judgment depends.

cs.CY · cs.MA

版本更新 · v2arXiv:2609.27976

Conformal Bayes under Continuous Label Shift: Sensitivity Analysis and the Limits of Exact Validity

Seungjin Choi

原文摘要

Conformal Bayes combines Bayesian posterior predictive scores with conformal calibration. Under continuous label shift, both the score and calibration weights depend on an unknown response density ratio. Existing methods typically estimate a single exponential tilt from pseudo-labels or predictive samples and plug it into calibration. We propose Joint Tilt-Sensitivity Conformal Bayes (JTS-CB), which performs sensitivity analysis over a prespecified family of tilts. Each tilt defines a coupled score-weight pair. The split procedure, JTS-SCB, solves joint min-max calibration by taking the largest tilt-specific threshold from weighted intercept-only quantile regression. JTS-Union retains individual thresholds, yielding prediction sets contained in those of JTS-SCB. Both use calibration-only weights by design, without a general coverage guarantee. We also study a candidate-weighted exact counterpart. Any nonzero linear exponential tilt makes its prediction set unbounded, whereas compact negative-quadratic families yield bounded exact unions under Gaussian scores. For the practical procedures, a localized correction with fallback gives coverage at least nominal minus a target tail-mass bound when the family contains the true tilt, but can substantially increase width. Experiments on controlled shifts of three regression datasets and on synthetic data show that plug-in predictive sampling can approach oracle coverage when the shift is well identified, but remains vulnerable to predictive bias and unstable tilt estimation. Sensitivity analysis can mitigate these failures in the tested settings, at the cost of wider prediction sets. Coupling scores and weights can yield narrower sets with higher coverage than varying weights alone, although this advantage is not uniform across shifts. Excluding the true tilt from the sensitivity family can still cause undercoverage.

stat.ML · cs.LG

版本更新 · v2arXiv:2605.10020

TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation

Wilson Wongso, Lihuan Li, Arian Prabowo, Xiachong Lin, Baiyu Chen, Hao Xue, Flora D. Salim

原文摘要

Generating high-fidelity synthetic Web of Things (WoT) telemetry, such as GPS trajectories, is increasingly important for transportation, urban planning, and location-aware services, particularly when privacy concerns restrict access to real-world mobility data. Existing trajectory generation methods face a trade-off between efficiency and road network fidelity: continuous-space methods generate trajectories efficiently but ignore road topology, while topology-aware methods rely on search-based autoregressive decoding that limits generation speed. We propose TrajDLM, a topology-aware trajectory generation framework based on block diffusion language models. TrajDLM represents trajectories as sequences of discrete road segments, combining a block diffusion backbone, graph-based road network representations, and topology-constrained sampling to generate realistic trajectories with topologically valid road transitions. To address the tendency of supervised models to favor near-shortest routes, we introduce TrajRFT, a rejection-sampling fine-tuning stage that improves route fidelity by training on self-generated routes selected for their similarity to real trajectories. Across three city-scale vehicle telemetry datasets, TrajDLM closely matches real-world mobility in population-level distributions, local route similarity, and route diversity, while generating trajectories up to $7.5\times$ faster than the strongest baseline. It also demonstrates zero-shot transfer to unseen transport modes. These results establish block diffusion with topology-constrained sampling and rejection-sampling fine-tuning as an efficient approach to generating realistic synthetic mobility telemetry for location-aware Web services and WoT applications.

cs.LG

版本更新 · v2arXiv:2604.16656

Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion

Maitrey Mehta, Nishant Subramani, Zhichao Xu, Ashim Gupta, Vivek Srikumar

原文摘要

All languages are equal; when it comes to tokenization, some are more equal than others. Tokens are the hidden currency that dictates the cost and latency of contemporary LLM access. However, many languages written in non-Latin scripts observe a poor exchange rate: LLMs take several multiples of tokens to encode the same information in many languages as they do for English. We observe that this issue, known as token overfragmentation, persists in modern open-weight LLMs. The standard remedy is vocabulary expansion that adds target language items missing from the model's vocabulary. We focus on two core decisions in the vocabulary expansion process: What items should we add? and How should we initialize their corresponding input and output embeddings? We comprehensively study and advance the new research direction of interpretability-based vocabulary expansion along these two core decisions, making four key contributions: First, we question the conventional use of frequency-based methods to choose candidate vocabulary items to add (a decision long treated as settled), and show that interpretability-based methods offer a superior performance-token efficiency tradeoff. Second, we strengthen the case for interpretability-based embedding initialization by showing large gains (~20 pts) over baseline initialization methods for several languages written in non-Latin scripts. Third, we identify the phenomenon of "subword detokenization," where models progressively merge fragmented subword tokens into larger subwords across layers. Fourth, we propose FragMend, a method that leverages this phenomenon to push the efficiency ceiling of interpretability-based expansion, and validate its effectiveness.

cs.CL

版本更新 · v2arXiv:2606.13799

The program is still there, and searching for it obeys a conservation law

Jorge Miguel Silva

原文摘要

The length of the shortest program that generates a sequence, its Kolmogorov complexity, is uncomputable, so we ask what finding a short program costs when one exists. Many search algorithms, including Levin search, evolutionary methods, simulated annealing and the cross-entropy method, learn about a candidate program only through its score, how much of the sequence it reproduces. For such algorithms we define the coupling width of a search problem, the largest number of program fields that must change together before the score moves. We prove an unconditional worst-case lower bound on the number of candidates scored, exponential in that width. Under stated conditions, a conservation law follows, in which each bit of structural knowledge injected into a search removes at most one bit of search. The structure plus the logarithm of the remaining search is at least a fixed fraction of the sequence's Kolmogorov complexity. That fraction tends to one as the instruction set grows, so the lower bound approaches Levin's 1973 upper bound, apart from the program's running time. Search by score must pay this cost to be complete. We prove that our engine's structural inference avoids it only by giving up coverage, as does, if one-way functions exist, every method that runs in polynomial time. Our deterministic engine, built on this theory, recovers a generating program, certified by compressing its data and predicting an unseen continuation, for 2,383 of 3,914 candidate sequences in four populations of integer sequences and cellular automata, including the chaotic Rule 30.

cs.CC · cs.LG

版本更新 · v2arXiv:2610.04536

WasserMan: Benchmark for Underwater Manipulation Policy Learning

Danil Belov, Artem Erkhov, Sergei Parsegov, Pavel Osinenko

原文摘要

Underwater contact manipulation couples visual decisions with vehicle stabilization and mechanism interaction. To our knowledge, WasserMan is the first multi-task simulation benchmark focused on visuomotor policy learning for manipulating articulated underwater mechanisms. The suite supports demonstration-based policy learning, alternative vehicle--arm platforms and bimanual manipulation. We compare ACT, diffusion policies and behavioral cloning under matched sample budgets, and evaluate adaptation of a pretrained SmolVLA baseline. Fixed-policy studies vary water appearance, lighting, contact parameters, actuator delay, arm properties and mechanism pose. RGB feedback controls and matched observation-history and expert-trajectory ablations examine observation and training choices. Expert references establish task feasibility under the same physical success tests. The experiments reveal task-dependent visual transfer and pose sensitivity, while contact, tracking and actuator measurements distinguish execution responses that completion alone hides. Complete expert candidate streams make the initial states associated with demonstration selection inspectable. Versioned code, demonstrations, checkpoints and per-episode physical evidence support reproducible comparisons within the simulation.

cs.RO

版本更新 · v3arXiv:2608.30621

Cost-efficient Active Learning for Referring Image Segmentation and Grounding

Junbeom Hong, Seonghoon Yu, Hyung Rok Jung, Sundong Kim, Jeany Son

原文摘要

Collecting natural-language referring expressions along with region annotations, such as masks or boxes, is a major bottleneck in visual grounding (VG), as annotators must write descriptions that distinguish target regions from visually similar ones. We tackle this by formulating active learning (AL) for VG under the realistic setting where only raw images are available without accompanying text. Since ground-truth text is unavailable, sample selection must estimate which images contain ambiguous regions that would require discriminative referring expressions. To address this, we generate auxiliary region-text pairs using foundation models, and introduce Referred Region Ambiguity, a new acquisition function that measures whether the model's confidence collapses onto a single region or disperses across multiple candidates. It allows our method to prioritize images with strong cross-region competition, which are more informative due to their visual ambiguity. We also design a referring-expression annotation interface that helps annotators quickly focus on writing discriminative language with a few clicks. Experiments on RIS and REC benchmarks show that our AL framework consistently outperforms several AL baselines, while a user study shows up to 1.6X faster description labeling of ours.

cs.CV · cs.AI

版本更新 · v3arXiv:2603.26638

RigidDriveGS: Object-Centric Vehicle Reconstruction from Fixed Multi-Camera Drive-Through Captures

Nitin Kulkarni, Akhil Devarashetti, Charlie Cluss, Livio Forte, Philip Schneider, Chunming Qiao, Alina Vereshchaka

原文摘要

High-fidelity 3D reconstruction of vehicle exteriors improves buyer confidence in online automotive marketplaces, but fixed multi-camera drive-through capture departs from standard Structure-from-Motion (SfM): static cameras observe a moving vehicle amid clutter, rotating wheels, fisheye distortion, and specular reflections. We present RigidDriveGS, an object-centric pipeline combining motion-gated tracking, bifurcated masks that exclude wheels for SfM while optionally retaining them for rendering, mask-guided dense correspondences on raw distorted images, rig-constrained global SfM, and clean object-centric neural rendering with trimap-aware opacity or density supervision and native-alpha white compositing. We evaluate 25 vehicles from 10 dealership installations and six phone-recorded vehicles, each captured from 14 independent handheld positions. Under a staggered per-camera temporal-block holdout, 3DGUT+MCMC achieves 30.42 dB PSNR, 0.90 SSIM, and 0.20 LPIPS, improving PSNR by 7.78 dB over undistorted 3D-GS; independently recorded reference LiDAR scans yield full/body Chamfer-L1 of 0.026/0.013 m and F1@5 cm of 0.703/0.885. These results support clutter-free, object-centric novel-view synthesis without controlled studio infrastructure.

cs.CV · cs.RO

版本更新 · v2arXiv:2610.32106

PersonaScienceBench: Evaluating Scientific Agents with Diverse Simulated Researchers

Siyang Wu, Weizhi Zhang, Chen Yang, Esther Xu Fei, Jorin Overwiening, Xu Pan, Jing Tang, Yixuan He 等 37 位作者

原文摘要

Scientific agents collaborate with researchers whose expertise and preferences differ, but benchmarks usually hold the collaborator fixed. We introduce PersonaScienceBench: 200 tasks from five benchmarks across four scientific domains. Simulated researchers provide context and feedback according to persona profiles, while task objectives and grading remain fixed. Agents encounter researcher preferences only through conversation. Across eighteen modelconfigurations, task performance, fact recovery, and self-repetition reveal different strengths. Detailed GPT 6 Astra analyses show distinct agent responses across researcher profiles; interaction traces illustrate targeted clar ification and workflow revision. These behaviors can differ even when final scores match. PersonaScienceBench therefore evaluates how agents collaborate with diverse researchers alongside whether they complete the task.

cs.AI

版本更新 · v3arXiv:2602.05842

Reinforcement World Model Learning for LLM-based Agents

Xiao Yu, Baolin Peng, Ruize Xu, Yelong Shen, Pengcheng He, Suman Nath, Nikhil Singh, Jiangfeng Gao 等 9 位作者

原文摘要

Large language models (LLMs) have achieved strong performance in language-centric tasks. However, in agentic settings, LLMs often struggle to anticipate action consequences and adapt to environment dynamics, highlighting the need for world-modeling capabilities in LLM-based agents. We propose Reinforcement World Model Learning (RWML), a self-supervised method that learns action-conditioned world models for LLM-based agents on textual states using sim-to-real gap rewards. Our method aligns simulated next states produced by the model with realized next states observed from the environment, encouraging consistency between internal world simulations and actual environment dynamics in a pre-trained embedding space. Unlike next-state token prediction, which prioritizes token-level fidelity (i.e., reproducing exact wording) over semantic equivalence and can lead to model collapse, our method provides a more robust training signal and is empirically less susceptible to reward hacking than LLM-as-a-judge. We evaluate our method on ALFWorld and $τ^2$ Bench and observe significant gains over the base model, despite using no expert data, task-success rewards, or strong-LLM annotations - only an off-the-shelf embedding model as a distance metric. When combined with task-success rewards, our method outperforms direct task-success reward RL by 6.9 and 5.7 points on ALFWorld and $τ^2$ Bench respectively; it further outperforms expert-data training on ALFWorld and is comparable to it on $τ^2$ Bench.

cs.CL

版本更新 · v4arXiv:2609.37788

A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses

Zhangshu Joshua Jiang, Zina Ibrahim, James T. Teo

原文摘要

We propose a rubric for assessing expressed clinical reasoning in model responses, drawing on three bodies of work: medical education assessment frameworks (ART, SCT, Key Feature Problems and OSCE); clinical LLM benchmarks (MedR-Bench, HealthBench, TIMER-Bench, DR. BENCH, PrIME-LLM and PatientSafeBench); and general LLM reasoning evaluation research, including the Factuality-Validity-Coherence-Utility taxonomy, FaithCoT-Bench and C2-Faith. We use groundedness as a clinically oriented adaptation of the taxonomy's factuality category. The rubric brings these concepts together in a multidimensional framework for scoring free-text responses to gold-standard clinical vignettes. It includes provisional behavioural anchors, applicability rules and a separate flag for case-specific safety-critical errors. General-domain frameworks inform its design but are not treated as validated clinical instruments. The rubric does not replace case-specific reference criteria or the task-specific metrics of existing benchmarks. It has not yet been tested for inter-rater reliability, construct validity or clinical utility. Its immediate purpose is to make evaluation decisions explicit and open to scrutiny before empirical testing.

cs.CL · cs.AI

版本更新 · v2arXiv:2605.06914

Pacing Branch Parallelism in LLM Serving

Swapnil Gandhi, Siva Kumar Sastry Hari, William J. Dally, Christos Kozyrakis

原文摘要

Recent methods expose intra-request parallelism in LLM outputs, allowing independent branches to decode concurrently. Existing serving systems execute these branches eagerly or under fixed caps. We show that both are brittle: eager admission inflates the shared decode step, degrading co-batched requests in serial stages, while conservative fixed caps forgo the throughput that motivated exposing branches in the first place. We call the excess step latency caused by admitted branches the \emph{branch externality} and show that the safe width depends on batch composition, context lengths, and accumulated slack, all of which change continuously over a workload trace. We introduce PACE, a per-step admission controller that treats extra branches as opportunistic width, admitted only when the predicted branch externality fits within the batch's current slack budget. Per-step regulation is practical because branch-level scheduling decouples compute from memory: branches share the request's prefix KV, so expanding or contracting width requires no memory reclamation. On Qwen3-32B, PACE improves goodput by $1.77\times$ over serving without branch parallelism and by $1.48\times$ over eager admission while maintaining 99\% SLO attainment. Comparable gains ($1.72$--$2.15\times$) hold on five additional dense and mixture-of-experts models with up to 671B parameters. Code is available at https://github.com/Swapnil-Gandhi/PACE

cs.DC · cs.AI · cs.CL

版本更新 · v2arXiv:2608.15428

Gated Against One Model, Open to the Next: Option-Only Solvability in Legal Multiple-Choice Benchmarks

Volodymyr Ovcharov

原文摘要

Multiple-choice benchmarks are graded on whether a model picks the right option, not on whether it needed the question. Measuring that gap takes care: a model answering A to most items scores above chance wherever the key sits at A, and reads as recognition when it is not. We measure it on UA-JudgeExam: 11,990 four-option items with official keys, published by Ukraine's Higher Qualification Commission of Judges. Shown the options and no question, Claude Haiku 4.5 scores 0.383 against chance, and the leak is concentrated: 11.8% of items are answered blind on all eight option orders, against 0.2 items expected by chance. It is not quotation: search over 280,059 editions of Ukrainian legislation recovers 0.128. Gating those out retains 8,128 items, on which the gating model itself now scores 0.204, while GPT-5.6, which took no part in the selection, still answers 0.515 of them with the question hidden. Scoring eighteen held-out models from eight vendors on the whole set and subtracting each one's position habit, four keep a sizeable excess: GPT-5.6 (+0.265), Gemini 3.1 Pro (+0.240), GPT-5.4 (+0.105), Sonnet 4.6 (+0.081); the rest stay within 0.031, and probes find no recall of the public bank behind it. Without the correction Llama 3.1 8B (0.292 blind, A on 92% of items) would read as a leaker. The gate does select something real: on the items it rejected, eleven of twelve models score 0.518-0.789, every interval clear of what the same model scores on the items it kept. But that signal is one model's, and filtering on it does not transfer upward. Rewriting distractors instead overshoots to 0.168, below chance and as exploitable. The same probe on LEXam returns chance: every option there points into the stem, none longer than 33 characters. Item format decides whether the problem can arise; capability decides how much is extracted. We release the corpus, predictions and harness.

cs.CL · cs.AI · cs.CY

版本更新 · v2arXiv:2511.08274

VeriCypher: Named-Entity Verification for GraphRAG via Text-to-Cypher Generation

Anton Gusarov, Anastasia Volkova, Valentin Khrulkov, Andrey Kuznetsov, Evgenii Maslov, Ivan Oseledets

原文摘要

Knowledge graph question answering has traditionally focused on Resource Description Framework (RDF) graphs, SPARQL queries, and triple-based representations. Labeled Property Graphs (LPGs), however, pose a different challenge for LLM-based query generation: executable Cypher queries must align with schema structure, traversal direction, property keys, and literal entity values. This motivated us to introduce VeriCypher, an LLM-based text-to-Cypher framework for question answering over LPGs. It combines query generation conditioned on Cypher-like graph schema summaries with runtime execution, LLM-based query evaluation, and iterative correction where the central mechanism is named-entity verification: the system extracts node labels, relationship patterns, property keys, and literal values from generated queries, checks them against the target graph and schema, and turns mismatches into correction instructions for the next generation step. We evaluate VeriCypher on the CypherBench benchmark across multiple domains and LLM backbones. Compared with an LLM baseline, this method consistently improves answer correctness and query robustness. Ablation results further show that named-entity verification helps correct hallucinated schema elements and entity values, supporting more reliable LLM-based question answering over heterogeneous property graphs.

cs.AI · cs.CL

版本更新 · v3arXiv:2507.02074

Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges

Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma

原文摘要

Crash detection from video feeds is a critical problem in intelligent transportation systems. Recent developments in large language models (LLMs) and vision-language models (VLMs) have transformed how we process, reason about, and summarize multimodal information. This paper surveys recent methods leveraging LLMs for crash detection from video data. We present a structured taxonomy of fusion strategies, summarize key datasets, analyze model architectures, compare performance benchmarks, and discuss ongoing challenges and opportunities. Our review provides a foundation for future research in this fast-growing intersection of video understanding and foundation models.

cs.CV · cs.AI

版本更新 · v2arXiv:2609.13890

Learning How Much to Collaborate: Difficulty-Aware Topology Selection for Multi-Agent Code Generation

Yunsong Hong

原文摘要

Multi-agent code-generation systems often use one communication topology for every problem. Across five topologies and 614 problems from APPS, HumanEval+ and LiveCodeBench, the advantage of hierarchical collaboration over a single agent grows from 2.4 points of pass@1 on the easiest third to 21.1 points on the hardest third, at about ten times the token cost. We propose the Difficulty-Aware Topology Selector (DATS), which predicts each topology's success probability and maximises predicted success minus cost. Its graph predictor treats topologies as nodes of a connectivity order. The complete graph-head comparison reports a 1.7-point advantage over a flat multi-label head while changing several mechanisms; capacity-matched adjacency controls show smaller descriptive differences. A scalar cost penalty can be recalibrated without retraining for approximately matched-spend comparisons when targets are attained. With a shared penalty, six methods span 21.6 percentage points of spend; two leading baselines fall behind DATS after method-specific calibration near the common target. At 40% of always-hierarchical cost, DATS reaches 77.7% pass@1 versus 73.6% for always-hierarchical and 74.3% for the strongest learned competitor. The main comparison includes Holm--Bonferroni-adjusted McNemar tests; unequal-cost differences do not imply matched-budget superiority. Backbone-specific gains are 4.07--4.23 points across four backbones. Alternatives to the 39 interpretable features, including a hybrid encoder, yield a largest observed gain of 1.3 points, with no significant pairwise improvement; this establishes neither equivalence nor an upper bound. A study on 400 mathematical reasoning problems reproduces difficulty-dependent collaboration gains, widening from 2.5 to 20.9 points.

cs.MA · cs.SE

版本更新 · v2arXiv:2610.06805

H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning

Wancong Zhang, Basile Terver, Michael Rabbat, Yann LeCun, Randall Balestriero

原文摘要

Long-horizon planning with latent world models requires reasoning across timescales and levels of abstraction. Existing task-agnostic JEPA world models predict and plan in a single latent space, often at a single timescale. We introduce H-JEPA, an end-to-end recipe for training a hierarchy of action-conditioned JEPAs in which each level predicts farther ahead in its own learned latent space. Planning proceeds top-down: the top level optimizes progress toward the goal, and each level's predictions become subgoals for the planner below it. When factors in the data evolve at separated timescales, higher levels discard fast, unpredictable detail and retain slower task-relevant state. Across four simulated navigation and manipulation environments, hierarchical planning improves over a flat JEPA; on Visual AntMaze, a three-level hierarchy raises success from 18% to 73% using less planner compute. Ablations attribute these gains to both temporal decomposition and higher-level goal representations. With inverse-dynamics supervision, the approach extends to diverse real-robot videos from DROID, where hierarchy improves offline planning fidelity at lower planner compute.

cs.LG · cs.RO

版本更新 · v2arXiv:2609.28761

KathDB-FAO: Optimizing Multimodal Queries through Operator Grouping and Code Reuse

Guorui Xiao, Douglas Brown, Artur Borycki, Magdalena Balazinska

原文摘要

Advances in multimodal large language models (multimodal LLMs) allow data systems to answer analytical queries over text and images alongside relational tables, but at a significant cost for large-scale data. Existing systems reduce this cost through rewrite rules written in advance, which cannot use the logic of an individual query or the semantics of the data it processes. To address this challenge, we design, implement, and evaluate KathDB-FAO, a query evaluation system over multimodal data. KathDB-FAO decomposes a complex query into an execution plan of fine-grained steps, which we call Function-as-Operators (FAOs). To reduce execution cost, it searches for subsets of these FAOs to implement together as one function, enabling query-specific optimizations that make fewer model calls. Synthesizing these functions with a frontier model has its own cost, yet we observe that synthesized FAOs often recur across queries. To further reduce plan generation cost, KathDB-FAO uses pre-built functions and reuses functions synthesized for earlier queries. On SemBench and an additional workload, KathDB-FAO achieves quality comparable to the strongest competing system while reducing end-to-end cost per query by 76% on average.

cs.DB · cs.AI

版本更新 · v4arXiv:2507.22524

HGCN(O): A Self-Tuning GCN HyperModel Toolkit for Outcome Prediction in Event-Sequence Data

Fang Wang, Paolo Ceravolo, Ernesto Damiani

原文摘要

Outcome prediction from event sequence data requires effective use of information at two distinct semantic levels: attributes of individual events and attributes of the complete sequence. Although graph models can explicitly represent temporal relations between events, existing approaches commonly rely on predefined representations and manually configured architectures, with limited consideration of how event and sequence information should be incorporated at their corresponding GNN levels or how GNN models should be fitted to different datasets without manual tuning. We propose HGCN(O), an end to end self tuning graph toolkit for hierarchical information representation and automated model configuration. Its core T-GCN architecture processes event information at the node level and sequence information at the graph level, while O-GCN provides a one level reference for early integration of sequence attributes. TP-GCN and TE-GCN extend T-GCN with a pseudo informative duration embedding and a learned activity embedding, respectively. HGCN(O) integrates these architecture specific designs with hypermodel optimization to jointly determine model structure and training configuration. The core T-GCN achieves F1 scores of 1.0000 on two balanced benchmarks and a weighted F1 of 0.8639 on a highly imbalanced dataset, compared with 0.8318 for GAT and 0.8453 for TransformerConv. Prefix and ablation analyses further demonstrate its effectiveness for outcome prediction from incomplete sequences and quantify the contributions of temporal edge weights and graph level sequence attributes.

cs.LG

版本更新 · v2arXiv:2605.19060

Efficient Factorized Volume Synthesis with Lifted Inter-Slice Feature Trajectories

Xinhe Zhang, Yuyang Zhang, Pengfei Jin, Arnau Marin-Llobet, Na Li, Quanzheng Li

原文摘要

High-resolution 3D medical image generation remains challenging because fully volumetric models are computationally expensive, while efficient 2D slice generators often fail to preserve anatomical consistency across the third dimension. We propose LiFT, a framework for Lifted inter-slice Feature Trajectories that factorizes 3D volume synthesis into per-slice image generation and inter-slice trajectory learning. Rather than using a fully volumetric synthesis backbone, LiFT treats a volume as an ordered trajectory in feature space, capturing how anatomical structures appear, transform, and disappear across depth. We demonstrate the LiFT framework in both unconditional and conditional settings. In unconditional generation, a tri-planar drifting loss matches feature distributions between generated and real volumes across three orthogonal planes; in paired translation, a bidirectional $z$-context mixer trained with paired target supervision supplies through-plane coherence while preserving per-slice fidelity. We evaluate LiFT on BraTS 2023 for unconditional and missing-modality MR synthesis, and on SynthRAD2023 for MR-to-CT translation. LiFT achieves competitive image quality while retaining the efficiency of predominantly 2D synthesis, operating up to $390\times$ faster than a volumetric diffusion baseline and consistently improving through-plane coherence through explicit inter-slice modeling. These results establish lightweight inter-slice trajectory learning as an efficient approach to high-resolution 3D medical synthesis.

cs.CV · cs.AI · eess.IV

版本更新 · v2arXiv:2502.16617

Optimal Kernel Learning for Gaussian Process Models with High-Dimensional Input

Lulu Kang, Minshen Xu

原文摘要

Gaussian process (GP) regression is a popular surrogate modeling tool for computer simulations in engineering and scientific domains. However, it often struggles with high computational costs and low prediction accuracy when the simulation involves too many input variables. For some simulation models, the outputs may only be significantly influenced by a small subset of the input variables, referred to as the ``active variables''. We propose an optimal kernel learning approach to identify these active variables, thereby overcoming GP model limitations and enhancing system understanding. Our method approximates the original GP model's covariance function through a convex combination of kernel functions, each utilizing low-dimensional subsets of input variables. Inspired by the Fedorov-Wynn algorithm from optimal design literature, we develop an optimal kernel learning algorithm to determine this approximation. We incorporate the effect heredity principle, a concept borrowed from the field of ``design and analysis of experiments'', to facilitate efficient computation. Through several examples, we demonstrate that the proposed method provides competitive prediction and variable selection, with favorable computational performance in the examples considered. It is an effective solution for interpreting the surrogate GP regression and simplifying the complex underlying system.

cs.LG · stat.ME · stat.ML

版本更新 · v2arXiv:2609.38379

Aligned Data Can Induce Misalignment via Context Confusion

Yavuz Bakman, Duygu Nur Yaldiz, Baris Askin, Swastik Roy, Morteza Ziyadi, Salman Avestimehr, Sai Praneeth Karimireddy

原文摘要

Large language models are frequently updated for various use cases, where filtering out misaligned training samples is a common practice for preventing post-update misalignment. However, alignment is inherently context-dependent: a behavior that is aligned in one context may be inappropriate in another. For example, recommending that researchers retain their data for reproducibility is aligned, whereas recommending that a mobile app retain users' sensitive data may violate users' privacy. Starting from this observation, we identify a posttraining phenomenon where aligned training induces misaligned behavior in other contexts. We call this phenomenon context confusion. We demonstrate context confusion across three domains: (1) Gender Equality, (2) Privacy, and (3) Physical Safety. Unlike the broad misalignment seen in emergent misalignment, context confusion causes domain-specific misalignment that evades general alignment evaluations. Further, it is not effectively reduced by injecting general alignment training data, but can be substantially reduced by including targeted alignment data for the misaligned domain or providing in-context learning examples during inference. Lastly, we provide a mechanistic explanation of context confusion. We observe that queries from different domains can undergo similar representational shifts during the fine-tuning. Consequently, a query from a different domain may activate the same behavioral feature learned during fine-tuning, which causes the behavior to transfer to a context where it is misaligned. Based on our findings, we argue that it is difficult to predict the alignment state of a model after training by inspecting the training data alone, which highlights the importance of comprehensive post-training alignment evaluations.

cs.AI · cs.LG

版本更新 · v2arXiv:2608.17014

"It just kind of shows that I went somewhere": An Exploratory Study of Fitness Data Visualization Sharing

Mara Solen, Thomas James Davidson, Emily Wall, Tamara Munzner

原文摘要

The sharing of curated fitness data posts occurs frequently on fitness-focused social platforms such as Strava and on general social media platforms such as Instagram, which is a novel context for visualization. To better understand the process of sharing and designing fitness data posts, as well as the role of visualization within them, we conduct 18 semi-structured interviews with fitness data sharers. From our thematic analysis of the data, we find three novel characteristics for visualization through our study of fitness data sharing: (i) the role of visualization as proof, (ii) the tension between individuality and conformity, and (iii) the complexity of design decisions with regards to effort and desire to share. We also discuss a set of design implications, including a need for more options for visualizations for activities without routes, more user control in fitness data sharing platforms, and maintained ease of use while increasing customization options.

cs.HC · cs.CY

版本更新 · v4arXiv:2507.02976

How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench

Amirali Sajadi, Kostadin Damevski, Preetha Chatterjee

原文摘要

Large language models (LLMs) and agentic frameworks are increasingly used for development tasks such as automated program repair (APR). Prior work has identified security risks in LLM-generated code, but most studies focus on synthetic, simplified, or isolated tasks. We present a large-scale security analysis of LLM-generated patches using 20,000+ GitHub issues from SWE-bench. We evaluate developer-written patches, two standalone LLMs (Llama 3.3 Instruct-70B and GPT-5.4 nano), and four agentic frameworks (OpenHands, AutoCodeRover, HoneyComb, and SWE-agent). We also analyze code, issue, and project-level factors associated with insecure patches. Under our evaluated SWE-bench setup, Llama 3.3 introduced 135 manually confirmed vulnerabilities across the train and test sets, compared with 12 in developer-written patches for the same issues. On the SWE-bench test set, GPT-5.4 nano introduced 3 vulnerabilities compared with 2 in developer patches. All four evaluated agentic frameworks also introduced vulnerabilities. OpenHands had the highest retained count, with 44 vulnerabilities across 11 issue instances. Vulnerabilities are associated with broader code modifications and with issues missing specific information. These results suggest that APR systems require proactive risk assessment methods that consider both generated code and issue context.

cs.CR · cs.LG · cs.SE

版本更新 · v2arXiv:2603.19461

Hyperagents

Jenny Zhang, Bingchen Zhao, Wannan Yang, Jakob Foerster, Jeff Clune, Minqi Jiang, Sam Devlin, Tatiana Shavrina

原文摘要

Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms, fundamentally limiting how fast such systems can improve. The Darwin Gödel Machine (DGM) demonstrates open-ended self-improvement in coding by repeatedly generating and evaluating self-modified variants. Because both evaluation and self-modification are coding tasks, gains in coding ability can translate into gains in self-improvement ability. However, this alignment does not generally hold beyond coding domains. We introduce \textbf{hyperagents}, self-referential agents that integrate a task agent (which solves the target task) and a meta agent (which modifies itself and the task agent) into a single editable program. Crucially, the meta-level modification procedure is itself editable, enabling metacognitive self-modification, improving not only the task-solving behavior, but also the mechanism that generates future improvements. We instantiate this framework by extending DGM to create DGM-Hyperagents (DGM-H), eliminating the assumption of domain-specific alignment between task performance and self-modification skill to potentially support self-accelerating progress on any computable task. Across diverse domains, the DGM-H improves performance over time and outperforms baselines without self-improvement or open-ended exploration, as well as prior self-improving systems. Furthermore, the DGM-H improves the process by which it generates new agents (e.g., persistent memory, performance tracking), and these meta-level improvements transfer across domains and accumulate across runs. DGM-Hyperagents offer a glimpse of open-ended AI systems that do not merely search for better solutions, but continually improve their search for how to improve.

cs.AI

版本更新 · v2arXiv:2601.16955

3D Molecule Generation from Rigid Motifs via SE(3) Flows

Roman Poletukhin, Marcel Kollovieh, Eike Eberhard, Stephan Günnemann

原文摘要

Three-dimensional molecular structure generation is typically performed at the level of individual atoms, yet molecular graph generation techniques often consider fragments as their structural units. Building on the advances in frame-based protein structure generation, we extend these fragmentation ideas to 3D, treating general molecules as sets of rigid-body motifs. Utilising this representation, we employ SE(3)-equivariant generative modelling for de novo 3D molecule generation from rigid motifs. In our evaluations, we observe results competitive with state-of-the-art bond-implicit methods, surpassing them in atom stability on GEOM-Drugs, while yielding a 2x to 10x reduction in generation steps and 3.5x compression in molecular representations compared to standard atom-based methods. We release our code at https://github.com/rpoletukhin/MotiFlow.

cs.LG

版本更新 · v3arXiv:2511.00917

MAESTRO: Orchestrating Robotics Modules with Coding Agents for Zero-Shot Generalist Robots

Junyao Shi, Rujia Yang, Kaitian Chao, Selina Bingqing Wan, Yifei Shao, Jiahui Lei, Jianing Qian, Long Le 等 12 位作者

原文摘要

Today's dominant route to generalist robots scales robotics data to train end-to-end policies. We instead use a vision-language model (VLM) as a coding agent that writes robot programs using a curated library of perception, planning, and control tools. MAESTRO's orchestration harness packages multi-step perception and action procedures into callable tools and guides their use through a plan-act-replan loop, using visual and execution feedback to verify outcomes and recover from failures. With this tool library and harness, MAESTRO matches or surpasses state-of-the-art vision-language-action (VLA) models zero-shot in our tabletop comparison and performs diverse mobile manipulation tasks, without collecting new teleoperation data or invoking a VLA tool. Ablations show that expanding the tool library improves average task progress with the full harness, while adding tools without it does not reliably improve progress. Case studies illustrate MAESTRO's potential for autonomous code improvement across trials, faster execution with VLA tools, and automatic robot data generation. We show that expanding robotics tool libraries together with their orchestration harnesses offers a complementary route to general-purpose robots alongside scaling end-to-end robot training data. Project site: https://maestro-robot.github.io. Code: https://github.com/penn-pal-lab/maestro.

cs.RO · cs.AI

版本更新 · v2arXiv:2505.22909

Learning to Charge More: How Q-Learning Firms Lock In Supracompetitive Prices

Cristian Chica, Yinglong Guo, Gilad Lerman

原文摘要

There is growing experimental evidence that $Q$-learning agents can learn to charge supracompetitive prices. We ask when such behavior persists, whether it emerges, and which strategies support it. In a repeated pricing game in which firms condition on the previous period's price profile, we give conditions on the learned action values under which supracompetitive prices become an absorbing state once experimentation ends. We then show that under softmax exploration these conditions are reached with positive and explicitly bounded probability, both from a random and from an all-zero initial $Q$-table. In the latter case firms lock in supracompetitive prices because they never learn that undercutting pays; the same mechanism can lock in the competitive price, so the long-run outcome is selected by the exploration path. Finally, we give sufficient conditions on the learned table under which the induced strategy is naive collusion, a grim trigger strategy or an increasing-price strategy; grim trigger strategies are subgame perfect under a standard discounting condition, whereas naive collusion is generally not an equilibrium.

econ.GN · cs.AI · cs.GT

版本更新 · v2arXiv:2606.06252

Can Test-Time Reconstruction Close the Loop on Latent Reasoning?

Xiaopeng Yuan, Haibo Jin, Ye Yu, Peng Kuang, Lijun Yu, Yushun Dong, Haohan Wang

原文摘要

Recent work moves intermediate reasoning from natural-language traces into latent or cache-level representations to reduce token overhead and avoid a discrete communication bottleneck. However, this shift also removes a key advantage of textual reasoning: intermediate states are no longer inspectable, making it difficult to determine whether a latent state still preserves the constraints of the original query. As a result, latent reasoning typically operates in an open loop, where a latent state is produced and consumed without an input-anchored fidelity check. We propose ReLAT (Reconstruction-Guided Latent Reasoning At Test Time), a self-supervised test-time training method that closes this loop using the query itself as the reference. Our key observation is that if a latent state faithfully represents a query, the query should be recoverable from it; if the query cannot be recovered, the latent state has lost task-relevant information. ReLAT operationalizes this principle by constructing a differentiable Question -> Latent Thought -> Question cycle and optimizing query reconstruction loss through the latent thought before answer generation. This anchors opaque latent computation to the problem specification it is supposed to represent. Across mathematical reasoning, knowledge QA, and code generation benchmarks on the Qwen family, ReLAT consistently improves over single-model inference, text-based collaboration, open-loop latent collaboration, and alternative test-time training objectives. On Qwen3-8B, ReLAT raises AIME 2024 accuracy from 56.7% to 73.3%, a 16.6-point gain over the strongest open-loop latent baseline.

cs.AI