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

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

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

统计口径与数据新鲜度

统计 2026-11-21 04:17 — 2026-11-22 04:17(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

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 8,992 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
版本更新 · v2arXiv:2610.32596

OWLS: Open-world Language-conditioned Speed Fields for Zero-Shot Rover Navigation

Chahyon Ku, Erica Tevere, Georgios Georgakis, Rudra Mukherjee, Bernadette Bucher

原文摘要

Semantics can provide a proxy for physical traversability. Terrain that looks like loose sand or a rock field is likely to have similar physical properties. Open-vocabulary vision-language models (VLMs) enable this physical reasoning over terrain outside any fixed label set. We present Open-world Language-conditioned Speed Fields (OWLS), which plans directly over the dense feature map of a VLM. Prompted with a description of traversable terrain, the VLM scores every pixel of a single camera image; OWLS projects these scores onto the ground, adapts them to the platform with two morphological operations, and uses the result as the speed field of a minimum-time planner, so terrain appearance and obstacle clearance shape one trajectory. OWLS needs no task-specific training, no terrain annotation, no persistent map, and no exteroceptive sensor beyond the camera. We evaluate it on a physical rover indoors and off-road, on simulated Mars and Moon rovers over 200 procedurally generated terrains, and on real planetary imagery. Project page: https://chahyon-ku.github.io/owls/

cs.RO

版本更新 · v3arXiv:2601.19831

Neural Neural Scaling Laws

Michael Y. Hu, Jane Pan, Ayush Rajesh Jhaveri, Nicholas Lourie, Kyunghyun Cho

原文摘要

Neural scaling laws predict how language model performance improves with increased training inputs. While aggregate metrics like validation loss can follow smooth power-law curves, individual downstream tasks exhibit diverse scaling behaviors: some improve monotonically, others plateau, and some even degrade with scale. We argue that predicting downstream performance from validation loss suffers from two limitations: averaging token-level losses obscures signal, and no simple parametric family can capture the full spectrum of scaling behaviors. To address this, we propose Neural Neural Scaling Laws (NeuNeu), a neural network that frames scaling law prediction as time-series extrapolation. NeuNeu combines temporal context from observed accuracy trajectories with token-level validation losses, learning to predict future performance without the limitations inherent in assuming a specific functional form. Trained entirely on open-source model checkpoints from HuggingFace, NeuNeu achieves 1.99% mean absolute error in predicting model accuracy on 66 downstream tasks -- a 44% reduction compared to logistic scaling laws (3.56% MAE). Furthermore, NeuNeu generalizes zero-shot to unseen model families, architectures, parameter counts, and downstream tasks. Our work suggests that predicting downstream scaling directly from data outperforms parametric alternatives.

cs.LG · cs.CL

版本更新 · v2arXiv:2606.15461

ESBMC-PLC: Formal Verification of IEC 61131-3 Ladder Diagram Programs Using SMT-Based Model Checking

Pierre Dantas, Lucas Cordeiro, Waldir Junior

原文摘要

Ladder diagram (LD) is the relay-circuit language of IEC 61131-3 in which many PLC safety interlocks are written, and model checkers built on SMT solvers do not read it. A verdict reached through a translation is only as good as that translation. We present ESBMC-PLC, which verifies LD programs with the ESBMC model checker, and argue that its translation is faithful. It encodes the scan cycle as a single loop with nondeterministic inputs, resolves graphical PLCopen XML networks into ordered rungs, models timers in milliseconds, and rejects programs outside an explicit subset. We prove, under eight stated hypotheses, that one iteration of the emitted loop agrees with one scan of a semantics for the subset, so scan-count verdicts on programs without user function blocks hold on that semantics. For timing-mode verdicts, a refinement theorem for MATIEC's timers gives evidence, not proof. One SMT query per program also compares the emitted loop with the C that MATIEC generates. On the 241 labeled LD variants of a public benchmark suite, ESBMC-PLC returns no wrong verdict against the current labels and proves 127 variants safe; ESBMC on MATIEC's C for the same programs proves 2. PLCverif with NuSMV, which shares neither our frontend nor ESBMC, agrees with ESBMC-PLC on all 207 of the 208 variants within the theorem's scope that it can run. On 413 LD programs from public GitHub repositories, none of the 104 that the per-program query can check differs from MATIEC. Every k-induction proof closes at k = 2. ESBMC's inductive step proves only properties that one scan preserves, so properties that depend on a longer history stay unproved.

cs.CL · cs.AR

版本更新 · v4arXiv:2510.04421

Learning Survival Models with Right-Censored Reporting Delays

Yuta Shikuri, Hironori Fujisawa

原文摘要

Survival analysis provides statistical methods to model the time until an event occurs. Reporting delays arise when event times are not observed at their occurrence but are only revealed upon reporting. This issue is particularly critical for timely risk evaluation when the observation window is short due to administrative censoring. In this study, we incorporate right-censored reporting delays by jointly modeling parametric hazards for the event and reporting processes. We then construct a consistent estimator for the model parameters and develop a Monte Carlo expectation-maximization algorithm to compute it. To address the challenges posed by administrative censoring, we leverage these findings and propose a transfer-learning procedure. Experimental results demonstrate that our method improves the accuracy of timely risk evaluation under administrative censoring.

stat.ML · cs.LG · math.ST

版本更新 · v4arXiv:2510.03953

Uniqueness and non-uniqueness of deriving transformations

Jean-Baptiste Vienney

原文摘要

A differential category is an additive symmetric monoidal category with an algebra modality, axiomatizing smooth functions, and a deriving transformation, axiomatizing the differentiation of these smooth functions. An algebra modality may or may not have both the nullary and the binary Seely isomorphisms. Lemay proved that if an algebra modality has both Seely isomorphisms, then it has at most one deriving transformation. It was then an open problem whether every algebra modality has at most one deriving transformation. We answer this question in the negative by constructing algebra modalities with infinite sets of deriving transformations. We also clarify the relations between the nullary Seely isomorphism, the binary Seely isomorphism, and uniqueness of deriving transformations (that is, the property for an algebra modality to have at most one deriving transformation). First, we refine Lemay's theorem by removing the assumption of the nullary Seely isomorphism. Then, we show by means of various examples that the six combinations of absence or presence of nullary Seely isomorphism, binary Seely isomorphism, and uniqueness of deriving transformations, which are not already ruled out by the refined uniqueness theorem, can be realized.

math.CT · cs.LO

版本更新 · v2arXiv:2609.17837

Adaptive hybrid coupling with operator inference, the overlapping Schwarz alternating method and reinforcement learning

Trishit Mondal, Irina Tezaur, Anthony Gruber

原文摘要

Hybrid domain decomposition methods provide a flexible framework for coupling full order models (FOMs) and reduced order models (ROMs), but typically assume the model assigned to each subdomain is fixed throughout a simulation. This is limiting for transient problems in which localized features propagate through the domain and the regions requiring high-fidelity resolution change over time. We introduce a reinforcement learning (RL)-based approach for online adaptation of FOM-ROM models coupled via the overlapping Schwarz alternating method (O-SAM), an iterative domain decomposition method that solves subdomain-local problems while exchanging solution information through transmission boundary conditions on overlapping interfaces. Deep Q-networks (DQNs) are trained offline to select among subdomain-local FOMs and pre-trained Operator Inference (OpInf) ROMs using a reward balancing accuracy, cost, and model-switching frequency. Once trained, the policies are deployed predictively on problem instances not seen during training, without requiring a reference FOM solution. We demonstrate the approach on two examples: a 1D advection-diffusion problem with a moving front, and a 3D linear elastic wave propagation problem implemented in the Norma.jl solid mechanics code. For the advection-diffusion benchmark, the learned policy dynamically allocates high-fidelity resolution as the front propagates and outperforms static FOM/ROM assignments; letting the agent also adapt the domain decomposition provides no further benefit. For the elastic wave benchmark, learned policies for two and three subdomain decompositions track the propagating wave by assigning FOMs to subdomains containing the wave and ROMs elsewhere, as expected. Our results demonstrate the potential of RL to enable predictive online adaptation of model fidelity within Schwarz-based hybrid simulations.

cs.LG · cs.AI · math-ph

版本更新 · v2arXiv:2602.19354

Between Commons and Property: Individual Image-Generation Model Creators' Perceived Accountability for Derivative AI Model on Open Model Marketplaces

Eun Jeong Kang, Fengyang Lin, Angel Hsing-Chi Hwang

原文摘要

Within the open model ecosystem, AI model marketplaces enable non-AI experts to create and distribute derivative AI models. These platforms establish RAI approaches that creators are expected to follow to prevent negative downstream effects from model deployment, yet such governance approaches often rely on creators' intrinsic motivation and integrity. Little is known about how individual creators conceptualize their accountability for derivative models and how these conceptualizations shape their RAI practices throughout the development cycle. Through semi-structured interviews with 19 creators of derivative image-generation models on open model marketplaces, we identify two distinct accountability logics underlying creators' development practices: commons-based peer production and personal creative property. Guided by these logics, creators engage with platform RAI approaches in ways that diverge from their intended purposes: they strategically repurpose attribution tools for model visibility rather than provenance transparency, displace platform authority in favor of community-based governance, restrict model access to manage downstream accountability costs, and treat RAI-related work as undervalued labor to be minimized. We discuss how self-regulatory use of RAI tools, shaped by individuals' perceptions, produces shortcomings, and how open model marketplaces might mitigate these limitations by structurally supporting creators' engagement with RAI practices.

cs.HC

版本更新 · v2arXiv:2605.15220

Always Learning, Always Mixing: Efficient and Simple Data Mixing All the Time

Michael Y. Hu, Apurva Gandhi, Kyunghyun Cho, Tal Linzen, Pratyusha Sharma

原文摘要

Data mixing decides how to combine different sources or types of data and is a consequential problem throughout language model training. In pretraining, data composition is a key determinant of model quality; in continual learning and adaptation, it governs what is retained and acquired. Yet existing data mixing methods address only one phase of this lifecycle at a time: some require smaller proxy models tied to a single training phase, others assume a fixed domain set, and continual learning lacks principled guidance altogether. We argue that data mixing is fundamentally an online decision making problem---one that recurs throughout training and demands a single, unified solution. We introduce OP-Mix (On-Policy Mix), a data mixing algorithm that operates across pretraining, midtraining, and instruction tuning. Our main insight is that candidate data mixtures can be cheaply simulated by interpolating between low-rank adapters trained directly on the current model, eliminating separate proxy models and ensuring the search is always grounded in the model's actual learning dynamics. Across the language model training lifecycle, OP-Mix consistently finds near-optimal mixtures while using a fraction of the compute of the baselines. In pretraining, OP-Mix improves upon training without mixing by 6.3% in average perplexity. For continual learning, OP-Mix matches the performance of both retraining and on-policy distillation while using 66% and 95% less overall compute, respectively. OP-Mix suggests a different view of language model training: not a sequence of distinct phases, but a single continuous process of learning from data.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2606.05415

Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval

Padmaja Jonnalagedda, Yuguang Yao, Xiang Gao, Hilaf Hasson, Kamalika Das

原文摘要

Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent schemas and formats, yet existing approaches either demand costly manual engineering or bypass structure entirely. We present a system that automatically discovers an executable schema from raw multi-source data and uses it as a shared contract for knowledge graph construction and query-time retrieval. A closed-world field catalog constrains LLM-based schema discovery to attested fields; deterministic structural analysis infers identity keys, foreign keys, and source hierarchy; and the resulting schema drives extraction, deduplication, and cross-source linking into a provenance-aware knowledge graph. At query time the schema -- optionally extended via a monotonic protocol -- conditions a multi-tool agent routing retrieval across structured lookup, graph traversal, and vector search, returning grounded answers with traceable citations. In controlled zero-shot comparisons using the same LLM, data, and evaluation harness, the system improves over retrieval-only and decomposition-based baselines across four QA benchmarks, with ablations showing that schema-conditioned routing, structural intelligence, and schema-guided construction each contribute to the gains.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2610.36477

Proposing Better Rollouts for On-Policy Distillation

Sirui Chen, Yunzhe Qi, Haobo Xu, Jiaru Zou, Mengting Ai, Zihao Li, Jingrui He

原文摘要

On-policy distillation (OPD) improves language-model post-training by letting the student learn from its own sampled trajectories under teacher supervision, aligning the training process with inference-time behavior. However, the rollout policy in OPD is usually treated as fixed: each round samples directly from the current student. We show that this choice can create a compounding teacher--student mismatch, because it requires the teacher to provide effective supervision on whichever trajectories the student samples, including ones less reachable by the teacher itself. On such trajectories, teacher supervision can become noisy or even misleading, leading to undesirable student patterns such as repetition. Moreover, since the updated student in turn defines the rollout policy of subsequent rounds, these patterns persist and potentially amplify over training. This failure mode suggests that improving OPD requires treating the rollout policy itself as an optimization target, rather than only modifying the distillation objective. We propose Mixture Proposal On-Policy Distillation (MPOPD), which derives a student-anchored, teacher-guided rollout distribution from a local trust-region objective based on relative teacher support. The resulting target is a geometric mixture of the student and teacher policies, and we introduce a proposal policy that approximates this mixture, enabling rollout generation in a single forward pass. Experiments on 16 math, knowledge, and medical reasoning benchmarks show consistent gains over OPD and recent variants. On math reasoning, our method improves average accuracy by 6.91 over OPD on Qwen3-4B-Base while reducing average generation length by 41%, suggesting that rollout policy design provides an effective way to improve OPD.

cs.LG · cs.AI

版本更新 · v3arXiv:2605.13047

Revealing the Gap in Human and VLM Scene Description through Counterfactual Semantic Saliency

Ziqi Wen, Parsa Madinei, Miguel P. Eckstein

原文摘要

Evaluating whether large vision-language models (VLMs) align with human perception for high-level semantic scene comprehension remains a challenge. Traditional white-box interpretability methods are inapplicable to closed-source architectures and passive metrics fail to isolate causal features. We introduce Counterfactual Semantic Saliency (CSS). This black-box, model-agnostic framework quantifies the importance of objects by measuring the semantic shift induced by their causal ablation from a scene. To evaluate AI-human semantic alignment, we tested prominent VLMs against a human psychophysics baseline comprising 16,603 valid responses across 307 complex natural scenes and 1,306 high-fidelity counterfactual variants. Our analysis reveals a pervasive scene comprehension gap: models exhibit an over-reliance (relative to humans) on object size, object centrality, and low-level saliency of objects. In contrast, models are less sensitive to the presence of people in the scenes than our human participants when describing the images. The over-reliance on object size is a primary driver explaining variations in model-human semantic divergence. Code and data are available at https://github.com/starsky77/Counterfactual-Semantic-Saliency-Data .

cs.CV · cs.AI

版本更新 · v2arXiv:2610.34321

TopX: Text-to-Motion for Unseen Skeletons from the Skeleton File Alone

Tengjiao Sun, Pengcheng Fang, Xiaoyu Zhan, Dongjie Fu, Xiaohao Cai, Hansung Kim

原文摘要

Text-to-motion models generate motion only for the skeletons they were trained on, while a new character arrives as a skeleton file and nothing else. We study text-to-motion for skeletons unseen in training, without clips of the character, templates, retargeting or fine-tuning. We present TopX, a 73M-parameter flow-matching transformer that generates joint rotations and a root trajectory for any skeleton from its kinematic tree, rest pose and joint names. Motion is normalised by the rest pose and the size of the skeleton, and the rest pose is encoded as a world-frame descriptor that is independent of how the rig's author oriented each joint, while rest conventions are randomised during training. Attention is factorised over the joints and the frames of a motion. Across joints, queries and keys are rotated by HK-RoPE, a heat-kernel rotary encoding of the skeleton graph that is defined for every tree and does not change with the order of its joints or the eigenbasis of its Laplacian; across frames, they are rotated by a rotary encoding of frame order. To evaluate this generalisation, we build SkelShift, which unifies four motion corpora under one codec and holds out whole skeletons, tree classes and species, so that each test bucket isolates one kind of skeleton shift: topology, joint count, body plan, species or rig source. It scores motion quality without a learned evaluator. A single model animates every benchmark skeleton (4--117 joints) directly from its skeleton file and generates up to 240 frames. On held-out game species its motion is about as close to the real clips as two halves of the real clips are to each other (kernel distance 0.127 against 0.124), and text-to-motion retrieval reaches R@1 0.953, compared with 0.929 for real motion. Project page: https://chdtevior.github.io/TopX-page/.

cs.CV

版本更新 · v2arXiv:2608.26257

Group Isomorphism and the Polylogarithmic-Time Hierarchy: Depth-2$\frac{1}{2}$ Circuits and Lower Bounds

Joshua A. Grochow, Gülce Kardeş, Michael Levet

原文摘要

In this paper, we investigate the low-depth circuit complexity of Group Isomorphism in the multiplication (Cayley) table model. We prove the first circuit lower bounds for Group Isomorphism: namely, we show that every family of depth-$2$ Boolean circuits deciding Group Isomorphism requires quasipolynomial-size. (We also extend this to a limited class of depth-3 circuits, namely $\textsf{CNF}$-of-$\textsf{XOR}$s.) We complement this with upper bounds of uniform depth-$2\frac{1}{2}$ circuits of quasipolynomial-size: depth 3 circuits with poly-logarithmic bottom fan-in. A sequence of previous results from 1970-2025 progressively reduced the circuit depth from polynomial to $3\frac{1}{2}$; all of these results relied on the generator-enumerator strategy and, in fact, applied more generally to quasigroups. In contrast, our depth-$2\frac{1}{2}$ construction follows a fundamentally different strategy that exploits structure more specific to groups. We guess a composition series for each group, together with generators for its terms and the isomorphism types of its composition factors. We then inductively verify that the corresponding extensions at each level of the two composition series are compatible. A central part in this approach brings to bear the extensive work on the Short Presentation Conjecture, in tandem with the algorithmic theory of group extensions and cohomology.

cs.CC · cs.DS

版本更新 · v2arXiv:2610.36340

CrowdCC: Jointly Benchmarking Corruption Robustness and Deployment Quantization in Crowd Counting

S Mahmudul Hasan, Lu Peng

原文摘要

Crowd-counting models deployed on edge devices face two challenges: inputs are degraded along the capture and transmission pipeline, while models are often quantized to satisfy resource constraints of the edge. Yet corruption robustness and deployment quantization are typically evaluated separately. We introduce CrowdCC, a controlled benchmark that jointly evaluates these effects across 23 deployment-motivated corruptions at three severity levels, four crowd-counting datasets, and 26 models. We evaluate TensorRT engines at FP32, FP16, and post-training INT8 precision on an A100 GPU, alongside throughput and energy measurements on corresponding Jetson Orin~NX configurations. The corruptions span six families, with head annotations adjusted when geometry or visibility changes. Our results show that capture-chain corruptions consistently cause the largest degradation across evaluated models, while crowd density affects absolute and relative errors differently. Accuracy on clean images does not reliably predict performance on the corresponding corrupted images. INT8 changes corruption robustness more than FP16, without a consistent direction, and does not consistently improve latency or energy efficiency. INT8 inference efficiency is strongly associated with reformat overhead in the compiled engine, with slowdowns also observed under limited INT8 coverage. Precision changes corrupted-error rankings and robustness--cost frontiers, highlighting the need to consider corruption robustness and deployment cost jointly when selecting models and precision. The code is available at https://github.com/Tulane-Computer-Architecture-Systems/CrowdCC-Release.

cs.CV · cs.AI

版本更新 · v2arXiv:2510.19793

A Logic-based Algorithmic Meta-Theorem for Treedepth: Single Exponential FPT Time and Polynomial Space

Benjamin Bergougnoux, Vera Chekan, Giannos Stamoulis

原文摘要

For a graph $G$, the parameter treedepth measures the minimum depth among all forests $F$, called elimination forests, such that $G$ is a subgraph of the ancestor-descendant closure of $F$. We introduce a logic, called neighborhood operator logic with acyclicity, connectivity and clique constraints ($\mathsf{NEO}_2[\mathsf{FRec}]+\mathsf{ACK}$ for short), that captures all NP-hard problems like Independent Set or Hamiltonian Cycle that are known to be tractable in time $2^{\mathcal{O}(k)}n^{\mathcal{O}(1)}$ and space $n^{\mathcal{O}(1)}$ on $n$-vertex graphs provided with elimination forests of depth $k$. We provide a model checking algorithm for $\mathsf{NEO}_2[\mathsf{FRec}]+\mathsf{ACK}$ with such complexity that unifies and extends these results. For $\mathsf{NEO}_2[\mathsf{FRec}]+\mathsf{k}$, the fragment of the above logic that does not use acyclicity and connectivity constraints, we get a strengthening of this result, where the space complexity is reduced to $\mathcal{O}(k\log(n))$. With a similar mechanism as the distance neighborhood logic introduced in [Bergougnoux, Dreier and Jaffke, SODA 2023], the logic $\mathsf{NEO}_2[\mathsf{FRec}]+\mathsf{ACK}$ is an extension of the fully-existential $\mathsf{MSO}_2$ with predicates for (1) querying generalizations of the neighborhoods of vertex sets, (2) verifying the connectivity and acyclicity of vertex and edge sets, and (3) verifying that a vertex set induces a clique. Our results provide $2^{\mathcal{O}(k)}n^{\mathcal{O}(1)}$ time and $n^{\mathcal{O}(1)}$ space algorithms for problems for which the existence of such algorithms was previously unknown. In particular, $\mathsf{NEO}_2[\mathsf{FRec}]$ captures CNF-SAT via the incidence graphs associated to CNF formulas, and it also captures several modulo counting problems like Odd Dominating Set.

cs.DS · cs.LO

版本更新 · v2arXiv:2610.32915

Eye Tracking Signal Quality Evaluation: Meta Quest Pro vs HTC VIVE Pro Eye vs HTC VIVE Focus Vision

Aleksandr Chernysh, Mehedi Hasan Raju, Kamrul Hasan, Md Arif Shahriar, Proloy Karmakar, Isayas B. Adhanom, Oleg Komogortsev

原文摘要

Gaze research in virtual reality needs eye trackers of known error. Thirty participants completed the same protocol on the Meta Quest Pro (QP), HTC VIVE Pro Eye (PE) and HTC VIVE Focus Vision (FV); to our knowledge, this is the first evaluation of the FV eye tracker. In a random-saccade task, median participant mean error was 1.04° on QP, 1.50° on PE and 2.41° on FV, which remained least accurate after linear recalibration. In a later block with a darker background, PE error rose by 0.70°. FV samples were positively correlated: dispersion was 9.8 times the sample-to-sample root mean square. The device clocks showed losses that mean error hides. QP paused for up to 6.04 s, and FV skipped single samples. During instructed eye closures, QP flagged every sample valid while gaze moved 9.74°. Evaluations should report repeated timestamps, loss composition on the device clock and validity during eye closures.

cs.HC

版本更新 · v2arXiv:2610.36801

API-TAIL: Detecting Model Substitution in LLM APIs through Temperature-Aligned Likelihood Tails

Haocheng Mei, Yuchuan Tian, Ye Yuan, Chao Xu, Allen Chen, Kai Han, Yunhe Wang

原文摘要

Commercial language model APIs return only text, allowing a provider to cut costs by quietly routing a fraction of user requests to a cheaper substitute model while billing for the advertised one. Detecting such partial substitution is challenging because honest providers also alter the output distribution through undocumented decoding and serving choices, such as temperature scaling, sampling truncation, repetition and presence penalties, and default system prompts, forcing an audit to test against a composite null of legitimate configurations rather than a single reference. Our key insight is that these legitimate variations primarily shift response typicality across the entire batch, whereas partial substitution injects individual responses that remain anomalous under the claimed model. Building on this, we introduce API-TAIL, a typicality audit that first absorbs batch-level shifts by aligning a single effective temperature to center standardized surprisal scores across the audited batch, and then flags the endpoint if the number of remaining tail responses exceeds a threshold calibrated across legitimate configurations. Evaluated on real-world API responses and constructed substitution mixtures, API-TAIL controls false alarms across diverse honest providers and detects low-rate partial substitution with a small query budget. Under a common composite calibration, it outperforms the adapted rank- and MMD-based audit baselines.

cs.LG · cs.CL

版本更新 · v4arXiv:2609.23290

Stochastic Flow Map for Count Data

Ganchao Wei

原文摘要

High-dimensional count data are common in scientific applications, but most diffusion and flow models are designed for continuous or categorical data, and generation often requires many sequential model evaluations. Here, we propose Count Flow Map, a generative model that learns finite-time transitions directly in count space for one- or few-step generation and transport between count distributions. Our model directly learns stochastic transitions over finite time intervals, using Poisson births and Binomial deaths to preserve nonnegative integer counts without a predefined maximum. These transition models are trained to match the underlying local birth--death dynamics and to maintain consistency across step sizes. We characterize the connection between local dynamics and finite-time transition consistency and derive a bound on the generation error. After validating Count Flow Map in several simulations, we apply it to single-cell drug perturbation prediction and neural population forecasting, where it captures perturbation responses and supports forecasts of high-activity events with only one or a few model evaluations. Together, these experiments demonstrate that Count Flow Map enables high-quality generation directly in count space across inference budgets, from one-step to few-step generation, using a single trained model.

stat.ML · cs.LG

版本更新 · v2arXiv:2609.05679

Quantum lower bounds for convex optimization and real matrix-vector query problems

Andrew M. Childs

原文摘要

We (the author and the AI systems that did the heavy lifting) show that the quantum query complexity of minimizing a convex function over a convex subset of $\mathbb{R}^n$ with evaluation and membership queries is $\tildeΩ(n)$, nearly matching the best known upper bound. In particular, we show this even for quadratic minimization, which is equivalent to inverting an $n \times n$ real matrix using matrix-vector queries. We also show linear or nearly linear lower bounds on the quantum query complexity of computing the trace, the sign of the determinant, and the magnitude of the determinant of a real matrix in the matrix-vector query model. We use a novel quantum lower bound technique, the determinantal witness method, based on identifying a witness whose Fourier transform vanishes on low-rank matrices and that correlates well with the function being computed.

quant-ph · cs.DS · math.OC

版本更新 · v2arXiv:2609.29332

Diverse Representation in Approval-Based Committee Voting

Julian Chingoma, Davide Grossi, Feline Lindeboom, Jan Maly

原文摘要

The study of approval-based committee voting has so far focused predominantly on proportional representation. The canonical notion of diverse representation, based on the Chamberlin-Courant score, counts the number of voters with at least one representative in the committee, making it an individualistic notion. We develop a more comprehensive theory that instead requires the representation of many groups of voters, grounding it in the justified representation (JR) axiom, which we strengthen in two directions. First, we study the existing axioms of Strong JR (SJR) and Semi-Strong JR (SSJR), which consider the same cohesive groups as JR but demand stricter representation. We show that neither can be optimized efficiently on general domains (unless P = NP), but both can be on the Candidate Interval and Voter Interval domain. Second, to capture the unique and defining opinions of a group, we introduce Distinctive Representation (DR) and its local optimization variant, Local DR. We address satisfiability and computation time, and show (Local) DR to be distinct from known proportionality and diversity axioms. Experiments on real-world and synthetic data show that Local DR performs well on multiple empirical measures of diversity.

cs.GT

版本更新 · v2arXiv:2610.24246

CoCoNet: Convex Conformal Network for Multi-Dimensional Uncertainty Regions

Alireza Moradi, Thomas Bruys, Pascal Van Hentenryck, Reza Zandehshahvar

原文摘要

Conformal prediction (CP) provides distribution-free coverage guarantees under exchangeability, but the efficiency of its prediction regions depends critically on the choice of the conformity score. This is particularly important in multivariate regression, where dependencies across output dimensions induce complex joint uncertainty structures. This paper introduces CoCoNet (Convex Conformal Network) for learning convex conformity scores that induce flexible, data-adaptive prediction regions. CoCoNet learns the score from held-out data by optimizing prediction-region efficiency while enforcing convexity with respect to the residual. CoCoNet then applies split-conformal calibration to retain finite-sample coverage guarantees. The paper presents two variants of the method: CoCoNet$_{\mathrm{Spline}}$, based on piecewise-linear scores, and CoCoNet$_{\mathrm{ICNN}}$, based on Input Convex Neural Networks. Experiments compare CoCoNet with other CP baselines over synthetic and real-world datasets with output dimensions ranging from 2 to 16. The results demonstrate the flexibility of CoCoNet in learning different response types. Across 8 models and 30 multi-dimensional regression tasks, CoCoNet$_\text{ICNN}$ and CoCoNet$_{\mathrm{Spline}\text{-}\ell_1}$ achieve the best efficiencies with average ranks of 1.45 and 2.75, respectively. In particular, CoCoNet$_\text{ICNN}$ ranks first on 22 tasks out of 30 in terms of efficiency.

stat.ML · cs.LG

版本更新 · v2arXiv:2610.35654

Improving JEV Entailment Reranking with Span Readouts and Selective Adaptation

Haocheng Mei, Yuchuan Tian, Ye Yuan, Enhua Wu, Chao Xu, Allen Chen, Kai Han, Yunhe Wang

原文摘要

JEV decision models pair a language model backbone with a lightweight scoring head to select among natural-language options. Direct selection compares candidate answers within one request, whereas entailment reranking evaluates each candidate in a separate natural language inference (NLI) request over fixed relation options. We examine whether the readout and adaptation choices used for direct selection remain effective for cross-request reranking. We combine a mean-span readout with selective backbone adaptation. Mean-span pooling replaces the option-ending pointer with an average of the contextualized states inside each NLI option, without adding head parameters. Selective adaptation retains low-rank updates in attention and gated DeltaNet projections while removing feed-forward adapters. On MC11, which averages accuracy over eleven reranking configurations from seven sources, selective adaptation improves NeoHorse-1-4B accuracy over the all-module baseline while cutting trainable parameters by more than half, and mean-span pooling yields further consistent gains at the same parameter count.

cs.CL

版本更新 · v3arXiv:2606.00686

Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing

Maryam Hashemzadeh, Jerry Huang, Minseon Kim, Marc-Alexandre Côté, Sarath Chandar

原文摘要

The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmful prompts. While effective at reducing immediate toxicity, this approach fundamentally constricts the model's epistemological scope, resulting in over-cautious systems that output uninformative blanket refusals to sensitive yet benign queries. In this work, we challenge the orthodoxy that unsafe data must be discarded. We propose a dialectical approach to alignment, positing that unsafe data encodes rich, domain-specific knowledge critical for nuanced, safe, and informative generation. To operationalize this, we introduce SafeMoE, a Mixture-of-Experts (MoE) framework that isolates unsafe knowledge into domain-specific Low-Rank Adapters (LoRA experts) trained exclusively on harmful corpora. To synthesize safety from these unsafe primitives, we train a lightweight gating network using a minimal, highly curated set of safe-informative responses (as few as 100 samples per domain). During inference, this router dynamically orchestrates the unsafe experts, effectively steering the generation trajectory toward safe outcomes while harnessing the experts' deep domain knowledge. Extensive empirical evaluations across stringent safety benchmarks demonstrate that SafeMoE is not only safer, achieving over a 20% relative improvement in safe response rate over the strongest baseline (RealSafe-R1 on PKU-SafeRLHF; more than a 15% absolute gain), but also produces more informative responses when safety and harmfulness are of paramount concern. Furthermore, the routing mechanism exhibits strong zero-shot generalization to unseen domains and broader safety tasks without domain-specific supervision. Our findings suggest a paradigm shift in alignment: true safety requires not the masking of unsafe knowledge, but its controlled integration.

cs.LG

版本更新 · v2arXiv:2511.21621

Two behavioural pseudometrics for continuous-time Markov processes

Linan Chen, Florence Clerc, Prakash Panangaden

原文摘要

Bisimulation is a concept that captures behavioural equivalence of states in a variety of types of transition systems. It has been widely studied in discrete-time settings where a key notion is the bisimulation metric which quantifies "how similar two states are". In [ 11], we generalized the concept of bisimulation metric in order to metrize the behaviour of continuous-time Markov processes. Similarly to the discrete-time case, we constructed a pseudometric following two iterative approaches - through a functional and through a real-valued logic, and showed that the outcomes coincide: the pseudometric obtained from the logic is a specific fixpoint of the functional which yields our first pseudometric. However, different from the discrete-time setting, in which the process has a step-by-step dynamics, the behavioural pseudometric we constructed applies to Markov processes that evolve continuously through time, such as diffusions and jump diffusions. While our treatment of the pseudometric in [11] relied on the time-indexed Markov kernels, in [ 8 , 9, 10 ], we showed the importance of trajectories in the consideration of behavioural equivalences for true continuous-time Markov processes. In this paper, we take the work from [11 ] further and propose a second behavioural pseudometric for diffusions based on trajectories. We conduct a similar study of this pseudometric from both the perspective of a functional and the viewpoint of a real-valued logic. We also compare this pseudometric with the first pseudometric obtained in [11].

cs.LO

版本更新 · v4arXiv:2608.12759

NavSight in the Wild: Understanding Real-World Use of a Mobile Augmented Reality Application for People with Low Vision in Outdoor Navigation

Yuheng Wu, Kexin Zhang, Ben Kosa, Ru Wang, Sanbrita Mondal, Yuhang Zhao

原文摘要

The ability to navigate outdoors safely and independently is crucial yet challenging for people with low vision (PLV). While various augmented reality (AR) systems for low vision have been designed and evaluated in ideal lab environments, no research has investigated their real-world feasibility and challenges. We present NavSight, a mobile AR application that assists PLV in outdoor navigation by recognizing important outdoor objects (e.g., curb, vehicle) and rendering real-time visual augmentations. Through a seven-day diary study with 12 PLV in real-world settings, we characterize the impact of NavSight on scene perception, users' configuration strategies on what objects to augment and how to augment them across scenarios, how users made sense of and responded to recognition errors, and the social acceptability of using NavSight in public. We further identify environmental factors affecting recognition, such as weather conditions, lighting and shadows, and nonstandard road markings and textures, as well as usability issues in daily use. We discuss these real-world challenges and derive design implications for future AI-powered assistive AR systems for outdoor use.

cs.HC

版本更新 · v3arXiv:2511.20709

DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents

Rupam Patir, Keyan Guo, Suvadra Barua, Abhijeet Pathak, Dinesh Gudimetla, Jiawei Guo, Hongxin Hu, Haipeng Cai

原文摘要

Large language models (LLMs) and LLM-based coding agents are now used to generate code from natural-language specifications, yet ensuring such code is both functionally correct and secure remains a challenge. We present DualGauge, the first fully automated framework for jointly evaluating correctness and security of specification-only code generation, supported by DualGauge-Bench, a language-agnostic benchmark of 307 coding tasks each paired with functional and security tests derived from the same specification. Evaluating 10 representative LLMs across Python, C++, and JavaScript, we find that functional correctness substantially overestimates reliable code generation: even the strongest model remains below 15% joint security-functionality success in every language. Common model-side factors--scale, extended thinking, quantization, instruction tuning, and code specialization--do not reliably improve joint performance, suggesting secure-and-correct code generation does not simply emerge from stronger coding capability. Evaluation of 3 leading coding agents (Codex, OpenHands, and Claude Code) shows that iterative scaffolding is not a reliable remedy on specification-only tasks: results are strongly scaffold-dependent, with two of the three agents failing to outperform a comparable direct model. A qualitative audit reveals that these failures concentrate at the output contract boundary and in guards that exist but are insufficient--patterns that only joint benchmarking reliably exposes.

cs.SE · cs.AI · cs.CR

版本更新 · v2arXiv:2603.22677

MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation

Di Zhu, Zihan Chen, Zixuan Li

原文摘要

Distributional metrics such as Fréchet Audio Distance cannot score individual music clips and correlate poorly with human judgments, while the only per-sample learned metric achieving high human correlation is closed-source. We introduce MUQ-EVAL, an open-source per-sample quality metric for AIgenerated music built by training lightweight prediction heads on frozen MuQ-310M features using MusicEval, a dataset of generated clips from 31 text-to-music systems with expert quality ratings. Our simplest model, frozen features with attention pooling and a two-layer MLP, achieves system-level SRCC = 0.957 and utterance-level SRCC = 0.838 with human mean opinion scores. A systematic ablation over training objectives and adaptation strategies shows that no addition meaningfully improves the frozen baseline, indicating that frozen MuQ representations already capture quality-relevant information. Encoder choice is the dominant design factor, outweighing all architectural and training decisions. LoRA-adapted models trained on as few as 150 clips already achieve usable correlation, enabling personalized quality evaluators from individual listener annotations. A controlled degradation analysis reveals selective sensitivity to signal-level artifacts but insensitivity to musical-structural distortions. Our metric, MUQ-EVAL, is fully open-source, outperforms existing open per-sample metrics, and runs in real time on a single consumer GPU. Code, model weights, and evaluation scripts are available at https://github.com/dgtql/MuQ-Eval.

cs.AI · cs.SD

版本更新 · v2arXiv:2610.37517

Orthogonal and Parametrized Multi-Attribute Steering of LLMs

Remy Ogasawara, Cullen Anderson, Narmeen Fatimah Oozeer, Foad Namjoo, Amir Abdullah, Jens Kristian Refsgaard Schou, Jeff M. Phillips

原文摘要

Activation steering offers an effective and efficient way to modify an LLM's behavior at inference time. However, it remains unclear how to apply steering such that the signal is consistently strong and the steering strength has a universally interpretable meaning. We address this first by identifying the most steerable interval for each steering vector and rescaling the steering range accordingly. Building on this, we introduce a more interpretable method for steering, called parameterized steering which instead of pushing activations in a direction, it sets them at the desired trait strength. Next, with multi-trait steering, we find that naively combining vectors causes them to interfere with one another. In response, we develop a method to orthogonalize the vectors; it decouples these traits, allowing a model to exhibit one behavior without inducing the others, thus enabling multiple traits to be steered simultaneously.

cs.LG · cs.AI

版本更新 · v2arXiv:2601.02304

Octopus: Agentic Multi-Table Discovery over Tabular Data Lakes

Wen-Zhi Li, Sainyam Galhotra

原文摘要

Tabular data discovery aims to identify the tables relevant to a natural-language question from a large collection of heterogeneous data. Existing systems typically assume that a question is answered by a single table and rely on retrieval pipelines constructed through substantial offline preprocessing. These assumptions become restrictive when relevant information is distributed across multiple tables. In this paper, we present Octopus, a lightweight agentic framework for multi-table data discovery. Octopus follows a thin-harness design that combines lightweight offline semantic guidance with adaptive access to raw tabular data. At query time, an LLM agent dynamically orchestrates semantic column search, structured tabular operations, and general-purpose execution to locate and verify relevant tables based on intermediate observations. We further introduce a benchmark that explicitly evaluates multi-table data discovery, covering both settings where multiple tables independently answer a question and settings where multiple tables must be joined. Experimental results across four independent-discovery datasets and two join-based datasets show that Octopus achieves the highest macro-F1 on all six datasets. It also substantially reduces offline preprocessing overhead relative to Pneuma and online latency and API cost relative to Claude Code. When coupled with the same NL2SQL agent, Octopus yields substantially higher downstream question-answering F1 than Claude Code, showing that improved table discovery provides more complete evidence for downstream analytics. Code is available at https://github.com/wenzhilics/octopus.

cs.DB

版本更新 · v2arXiv:2604.01169

Bridging the Simulation-to-Experiment Gap with Generative Models using Adversarial Distribution Alignment

Kai Nelson, Tobias Kreiman, Sergey Levine, Aditi S. Krishnapriyan

原文摘要

A fundamental challenge in science and engineering is the simulation-to-experiment gap. While we often possess prior knowledge of physical laws, these physical laws can be too difficult to solve exactly for complex systems. Such systems are commonly modeled using simulators, which impose computational approximations. Meanwhile, experimental measurements more faithfully represent the real world, but experimental data typically consists of observations that only partially reflect the system's full underlying state. We propose a data-driven distribution alignment framework that bridges this simulation-to-experiment gap by pre-training a generative model on fully observed (but imperfect) simulation data, then aligning it with partial (but real) observations of experimental data. While our method is domain-agnostic, we ground our approach in the physical sciences by introducing Adversarial Distribution Alignment (ADA). This method aligns a generative model of atomic positions -- initially trained on a simulated Boltzmann distribution -- with the distribution of experimental observations. We prove that our method recovers the target observable distribution, even with multiple, potentially correlated observables. We also empirically validate our framework on synthetic, molecular, and experimental protein data, demonstrating that it can align generative models with diverse observables. Our code is available at https://kaityrusnelson.com/ada/.

cs.LG · cond-mat.mtrl-sci · q-bio.BM