跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+979新增论文
+781其中 AI 相关
+119已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 02:13 — 2026-11-21 02:13(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:2026-11-20 08:48最近发现新增版本:2026-11-20 19:58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。

28,961 已收录论文24,030 AI 相关8,912 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 21,358 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
版本更新 · v2arXiv:2605.00367

Flow matching for Sentinel-2 super-resolution: implementation, application, and implications

Dakota Hester, Vitor S. Martins, Lucas B. Ferreira, Thainara M. A. Lima, Juliana A. Araújo

原文摘要

Developing robust techniques for super-resolution of satellite imagery involves navigating commonly observed trade-offs between spectral fidelity and perceptual quality. In this work, we introduce a flow matching model for 4x super-resolution of 10-m Sentinel-2 visible and near-infrared bands over the conterminous United States (CONUS) using a dataset of 120,851 10-m Sentinel-2 and 2.5-m resampled NAIP imagery pairs acquired on the same day. Our results showed that the flow matching model outperformed diffusion and Real-ESRGAN models in pixel-wise accuracy in a single sampling step using the Euler method, closely approaching the performance of a dedicated supervised regression baseline. When evaluated with a second-order Midpoint solver, our model generated perceptually realistic super-resolved imagery in only 20 sampling steps, effectively navigating the perception-distortion trade-off at inference time without retraining. We used this model to produce a super-resolved 2.5-m 4-band CONUS imagery product derived from 2025 10-m Sentinel-2 annual composites, consisting of over 1.58 trillion pixels. We further evaluated the use of super-resolved data on a land cover classification task using semantic segmentation models. Finally, we generated a yearly 2.5-m land cover product for the Chesapeake Bay watershed for 2020-2025. An accuracy assessment against 25,000 ground truth points revealed an overall accuracy of 89.11% for the 2021 and 2022 land cover data. We conclude that flow matching is an effective generative modeling approach for super-resolution of Sentinel-2 imagery compared to diffusion and Generative Adversarial Network-based methods, and has strong implications for expanding access to high-resolution imagery for geospatial applications that demand fine spatial detail.

cs.CV

新论文 · v1arXiv:2611.22039

RLDE: A Reinforcement Learning Framework for Interpretable Iterative Document Editing

Nikhil Parkar, M. Marimuthu, Riya Joshi, Karthikeyan N

原文摘要

Improving the quality, clarity, and flow of long documents remains a challenging problem in NLP, as human editing typically occurs through iterative refinement rather than a single-pass rewrite. Most existing automated systems act as black-box generators or rely on supervised learning, limiting interpretability and failing to capture the sequential nature of revisions. In this paper, we propose RLDE, an automated end-to-end metric-driven RL framework that formulates document revision as a reference-free MDP problem (unsupervised with respect to paired document-revision targets). Working with a limited action space (NOOP, INSERT, DELETE, REPLACE), RLDE leverages Pointer Networks for dynamic span selection at the token level and sends generative actions to the frozen BART-base model to obtain context-aware suggestions. PPO agents learn to optimize a multi-objective reward function based on readability, perplexity, and grammar metrics with the help of a novel SBERT-based Semantic Preservation Penalty constraint to avoid deletion degeneracy. Evaluations on the BEA-2019 dataset showed statistically significant results (p < 0.01) across all metrics, where Flesch Reading Ease increased from 49.8 to 59.4, perplexity decreased from 63.7 to 39.8, while preserving 93% of semantic information. When compared to Chain-of-Thought (CoT) prompt-engineered models like GPT-4 and LLaMA-2, RLDE shows high performance at a very low computational inference cost. Moreover, the quality of edits generated by RLDE has been verified via human evaluations, scoring 4.9/5 for meaning preservation and 4.4/5 for edit quality.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.22038

GP--RL--MPC: Uncertainty-Aware Reinforcement Learning-Augmented Model Predictive Control with Gaussian Process Postdecision State-Value Functions

Jon Li, Jay H. Lee

原文摘要

We propose Gaussian Process Reinforcement Learning-Augmented Model Predictive Control (GP--RL--MPC), which uses a learned critic as the MPC terminal penalty to account for costs beyond the prediction horizon. Gaussian process regression (GPR) enables data-efficient critic learning from limited, noisy rollouts within optimistic approximate policy iteration (OAPI), with soft updates mitigating policy chattering. A tunable risk coefficient weights GP epistemic uncertainty in the terminal cost, regulating sensitivity to uncertain critic predictions. The postdecision state formulation shifts disturbance averaging offline to account for aleatoric uncertainty from the terminal transition onward. Under matching objectives and admissible actions, a one-step horizon recovers greedy value-space RL. After fitting GP hyperparameters by exact marginal likelihood, we construct a sparse deterministic training conditional (DTC) posterior using inducing points selected by pivoted Cholesky (PC), reducing online evaluation costs as the training dataset grows. In a continuous stirred-tank reactor (CSTR) subject to exogenous disturbances, GP--RL--MPC with an appropriately selected risk coefficient and policy screening reduces the sum of squared errors (SSE) by an average of 80.52% relative to an otherwise matched baseline MPC across five random seeds (sample standard deviation: 3.48%).

cs.LG · eess.SY

版本更新 · v2arXiv:2605.09079

Scaling Causal Reasoning with Increasingly Complex Causal Simulators

Nicolás Astorga, Anita Kriz, Mihaela van der Schaar

原文摘要

Despite surpassing human performance across mathematics, coding, and other knowledge-intensive tasks, large language models (LLMs) continue to struggle with causal reasoning. A core obstacle is the target data itself: causal systems are complex and often expressed in non-executable forms, while ground-truth answers to causal queries are inherently scarce. We introduce CauSim, a framework that turns causal reasoning from a scarce-label problem into a scalable supervised one. CauSim constructs increasingly complex causal simulators: executable structural causal models (SCMs), incrementally built by LLMs, that scale to globally complex systems while maintaining verifiable answers to causal queries. CauSim operates across representations by formalizing non-executable causal knowledge into code, enabling data augmentation, and translating executable SCMs into natural language, enabling supervision in previously difficult-to-supervise representations. We structure our research into two parts: (1) how to construct increasingly complex causal simulators, and (2) a systematic study of what CauSim enables, demonstrating generalization across representations, consistent gains from curriculum scaling and data volume, LLM self-improvement through self-generated simulators, and data augmentation via formalization of existing domain knowledge.

cs.AI

版本更新 · v2arXiv:2611.08879

GeoJeV: Unified Spatial Probability for Training-Free Efficient Evidence Acquisition in Ultra-High-Resolution Remote Sensing

Xinyi Niu, Lingfeng Chen, Jiehua Zhang, Panhe Hu, Li Liu, Zhen Liu, Yongxiang Liu

原文摘要

Ultra-high-resolution (UHR) remote sensing imagery provides rich spatial details but poses challenges for accurate and efficient multimodal understanding. Existing evidence acquisition methods selectively explore relevant image regions, yet largely rely on generative multimodal large language models (MLLMs) for intermediate search control. However, reinforcement learning from human feedback (RLHF) primarily aligns these models with human-preferred responses rather than explicitly optimizing region-level relevance judgments, while repeated autoregressive decoding introduces additional computational overhead. To address these limitations, we propose GeoJeV, a training-free method that formulates evidence acquisition as spatial probability-driven decision making. At each evaluated region, a frozen JeV model produces a probability distribution over candidate regions. Specifically, Region Rank prioritizes candidate regions, Sparse Branch adaptively determines branching width through sparse probability support, and Depth Gate controls refinement depth based on branch sparsity and distribution concentration. By coordinating search priority, branching width, and refinement depth through a shared distribution, GeoJeV reduces reliance on RLHF-aligned generation and eliminates intermediate decoding. Experiments on LRS-GRO, MME-RealWorld-RS, and LRS-VQA achieve accuracies of 60.59%, 52.79%, and 34.32%, respectively. Across the three benchmarks, GeoJeV improves the average accuracy of Qwen3-VL-8B by +5.32pp with only 1.12 additional seconds per question, while achieving a 7.8-fold inference speedup over the recent method.

cs.CV · eess.SP

版本更新 · v2arXiv:2606.05464

Optimization-like Reasoning in LLMs over Expanding Search Spaces

Nicolás Astorga, Nabeel Seedat, Mihaela van der Schaar

原文摘要

Verifiable reward training has improved mathematical and coding reasoning, but these domains capture only part of step-by-step decision making. Many real-world tasks require finding a high-value feasible plan among many valid alternatives. We introduce OPT*, a scalable family of optimization-style tasks for training and evaluating LLM step-by-step optimization-like reasoning along a complexity axis: each task provides a feasibility checker and evaluator, while a complexity parameter expands the search space without requiring new human labels. This motivates studying these tasks in two regimes: (i) solver-guided online policy optimization, which uses a solver as a value oracle for partial states and applies rank-based reward shaping to reinforce better next steps, and (ii) search-based offline RL when such solvers are unavailable. Theoretically, we relate success in large search spaces to the information a reasoner extracts per unit of search budget. Empirically, we ablate the ingredients that make search efficient on OPT* and show that training on OPT* improves step-by-step optimization-like reasoning.

cs.AI

版本更新 · v2arXiv:2606.26525

Theory-Scale Auto-Formalization of Logic for Computer Science

Yuming Feng, Frederick Pu, One An, Osbert Bastani, Li Zhang, Jiani Huang, Xujie Si, Ziyang Li

原文摘要

Auto-formalization is critical for scalable formal verification, but existing progress largely focuses on isolated statements, while theory-scale auto-formalization, which coherently translates hundreds of interdependent definitions, lemmas, and theorems, remains open due to challenges in consistency, faithfulness, scalability, and correctness. In this paper, we introduce LCS-Bench, a stand-alone, theory-scale benchmark based on Logic for Computer Science. LCS-Bench is built through a novel semi-automated agentic pipeline that leverages concept graphs, formal signature planning, issue tracking, sorry-filling with counter-example search, complemented by faithfulness review from human experts. The resulting artifact covers 327 textbook items, over 4,076 Lean declarations, and more than 85K lines of Lean code. The dataset supports broad evaluation through a data engine that automatically derives five tracks of evaluation benchmarks, measuring different aspects of auto-formalization and theorem-proving capabilities. We also introduce a novel evaluation protocol featuring definitional equivalence checkers, enabling more fine-grained and faithful assessment. Through extensive evaluation on 17 models, we demonstrate that (1) LCS-Bench is of high quality, consistent, and faithful; (2) the benchmark is challenging, with state-of-the-art models achieving only 20.3% on auto-formalization tasks; and (3) our analysis reveals key findings regarding theory-scale auto-formalization and suggests promising directions for future work.

cs.LG · cs.LO · cs.PL

新论文 · v1arXiv:2611.22030

What Does an Agent Need? Bundle-Aware Agent Resource Composition

Yunxiao Shi, Tingwei Chen, Dannong Xu, Ahad N. Zehmakan, Jialie Shen, Zhendong Chu, Qingsong Wen

原文摘要

An agent resource's value depends on its backbone and companion resources and is known only after execution. Token-based generators remain tied to their training catalog, while independent resource scoring misses complementarities and reused bundles target other tasks. We formulate Task-Conditioned Agent Resource Composition (AgentComposition): jointly selecting a backbone model and a tool-skill bundle to maximize end-to-end execution utility. Our Retrieval-Grounded Bundle-Aware Agent Generation retrieves candidate resources and past configurations of similar tasks. A fine-tuned generator reads resource descriptions and recombines candidates through constrained beam search, allowing new resources without retraining. A bundle-aware critic ranks complete configurations using a large language model (LLM) teacher and historically successful configurations as execution proxies, and adapts to execution feedback when available. We evaluate reference recovery, offline execution with judged and native rewards, and online recommendation with real execution, building AgentSelect-Exec with 5,060 executed configurations. Our method recovers the complete reference configuration within ten candidates for 67.73% of AgentSelect queries, nearly twice the strongest baseline, and leads all baselines on SkillsBench. The proxy-trained critic raises the top-ranked agent's execution score from 7.58 to 8.37 out of 10; execution feedback increases it to 8.78, above the strongest baselines. Four target-domain queries suffice to adapt the generator to SkillsBench. Agents recommended online outperform the strongest baselines under both an LLM judge and native verifiers. These results support learning and transferring joint resource composition from task experience.

cs.AI

新论文 · v1arXiv:2611.22028

BATMoS: Budget-Aware Guidance Allocation for Efficient Video Diffusion

Zhixu Du, Kuo Yang, Jingwei Sun, Hai "Helen" Li, Yiran Chen

原文摘要

The effectiveness of a video diffusion model's inference budget depends on where computation is spent along the denoising trajectory. Across eight equal-budget inference configurations, VBench total scores span 4.80 points, highlighting the importance of explicit allocation design. Our key insight is that guidance evaluations are not equally valuable across diffusion time: retaining the sampling updates while selectively reusing guidance can preserve generation quality with fewer denoiser evaluations. We introduce BATMoS (Budget Aware Temporal Mixture of Strategies), which routes between fresh classifier-free guidance and cached guidance using a single pretrained denoiser. A magnitude-based temporal rule assigns guidance reuse to low-magnitude blocks and reserves fresh guidance for the remaining blocks, with a single integer controlling the computation budget. The resulting schedule requires no additional router training or per-budget threshold search. Evaluated on CogVideoX-2B with 4,720 videos per configuration across all sixteen official VBench dimensions, BATMoS achieves the highest total score among the eight allocation policies and comes within 0.10 points of full classifier-free guidance using 20\% fewer branch evaluations. BATMoS also composes with feature reuse, reducing computation from 80 to 62 effective branch evaluations with a 0.11-point decrease in total score. These findings make temporal guidance allocation a practical mechanism for extracting more generation quality from a fixed inference budget.

cs.CV

版本更新 · v2arXiv:2507.15448

Frames over finite fields with respect to the Galois inner product and their connections to self-orthogonal and LCD codes

Junmin An, Jon-Lark Kim

原文摘要

In this paper, we generalize the theory of frames to vector spaces over finite fields equipped with the $\ell$-Galois inner product. We introduce $\ell$-Galois analogues of fundamental concepts in frame theory and investigate extensions of existing results to the $\ell$-Galois setting. In particular, we establish necessary and sufficient conditions for a given matrix to be the $\ell$-Galois Gram matrix of a frame and show that such frames are unique up to isometry. We also extend Gerzon's bound to $\ell$-Galois equiangular systems and show that equality in this bound yields an $\ell$-Galois equiangular tight frame. Furthermore, we investigate the connections between $\ell$-Galois frames and $\ell$-Galois self-orthogonal and LCD codes over finite fields. We establish necessary and sufficient conditions for constructing $\ell$-Galois equiangular tight frames from self-dual codes, generalizing existing results by Shi et al. on the relationship between frames and self-dual codes over finite fields. Beyond self-dual codes, we provide sufficient conditions for constructing $\ell$-Galois equiangular tight frames from linear codes using their automorphism groups, together with explicit examples.

cs.IT

版本更新 · v3arXiv:2603.17673

Towards Reliable Local Security Agents: Verifiable Post-Training for Linux Privilege Escalation

Philipp Normann, Andreas Happe, Jürgen Cito, Daniel Arp

原文摘要

LLM agents are increasingly important in security, yet leading systems are typically closed-source and cloud-hosted, limiting reproducibility and their use with sensitive data. This creates a need for small, local models that can perform security tasks under strict resource constraints, though effective methods for developing them remain underexplored. In this paper, we address this gap by proposing a two-stage post-training recipe that turns a small local language model into a security agent. To this end, we focus on Linux privilege escalation as a representative setting to systematically study the training of local models, as the task is automatically verifiable and requires multi-step interactive reasoning. Using an experimental setup that mitigates benchmark leakage, we post-train a small 4B model in two stages: supervised fine-tuning on traces from procedural privilege-escalation environments, followed by reinforcement learning with verifiable rewards. On a held-out benchmark of 12 Linux privilege-escalation scenarios, supervised fine-tuning nearly doubles the baseline success rate under a tight budget of 20 interaction rounds, and subsequent reinforcement learning improves our model, PrivEsc-LLM 4B, to 93.3% success, ahead of all other evaluated models that fit a single consumer GPU. At the same time, its expected inference cost per successful escalation is more than 80x lower than that of Claude Opus 4.7. Our findings show that small local models can be adapted to complex security tasks. We document the challenges involved and offer guidance for transferring this recipe to other settings.

cs.CR · cs.AI

新论文 · v1arXiv:2611.22019

Computed Permutation Trellis Coding: Near-Optimal Quantization from Two Multiplications and a 64-Byte Table

Muhammed Fatih Balın

原文摘要

We propose Computed Permutation Trellis Coding (CPTC), a low-bit quantization format for tensors written once and read many times. Formats that round each value on its own, such as INT4 and FP4, waste a large part of their bits against the information-theoretic ideal. Trellis codes recover this loss by encoding values jointly, but prior decoders either need a large lookup table for their best quality or compute values with a hash that restricts what they can decode. CPTC's decoder multiplies its state by two coefficients and adds the top bits of the products to index a 64-byte table. Because that sum is not uniformly distributed, the rarely used ends of a small table can hold values far out in the tails. One decoder serves every bit width from 1 to 6, reproduces the standard integer and floating-point formats exactly, and comes within 0.07 bits of the ideal at 4 bits. It matches a random-permutation trellis code whose table is thousands of times larger, and exceeds every QTIP codebook. In LLM weight quantization without fine-tuning, CPTC has the lowest KL divergence to the unquantized model at every tested bit width on Llama 3.1 8B and 70B Instruct against QTIP's codebooks (by up to 27%). The decoder has been built into the AWS Trainium 4 AI accelerator, where it runs at the throughput of the native FP4 and FP8 formats for a negligible fraction of the systolic array's area. Fused encoding kernels quantize an 8B model's linear layers in under two minutes on one GPU and, in cycle-level simulation, on one Trainium 4 chip.

cs.IT · cs.AI · cs.AR · cs.LG

新论文 · v1arXiv:2611.22017

SkillBuffBench: Measuring What Agent Skills Contribute across Harnesses, Models, Skill Access Modes and Memory

Gengyue Dong, Ye Wei, Zheng Zhu, Yidong Han, Jiale Miao, Xiaojun Jia, Guanghui Li

原文摘要

Agent Skills, file-based packages of procedural knowledge that a coding agent can discover and load on demand, are now shipped by every major agent harness, yet the evidence for how much they help comes almost entirely from settings in which the right Skill is hand-picked for the task and the agent starts from a blank slate. Neither holds in deployment, where an agent chooses from whatever library happens to be installed and frequently carries memory from earlier work. We present SkillBuffBench, a benchmark and paired evaluation protocol that treats Skill access as a three-level factor (no Skill, a curated Skill, and automatic invocation from an installed library), crosses it with memory (off and on), with four agent harnesses and with multiple models (the state-of-the-art proprietary models from Anthropic, Google and OpenAI, and the state-of-the-art open-weight models from Chinese providers), every model being run under every harness, and evaluates the result on research tasks contributed by domain experts together with the Skills they use, currently in materials science and biology, with the suite extended on a rolling basis. Every run is marked by a deterministic verifier; uncertainty is reported with a paired, task-level bootstrap; and cost, agent rounds and wall-clock time are reported alongside the score rather than folded into it. This version of the paper describes the design of the benchmark, its evaluation protocol and its current tasks and Skills. The evaluation is in progress: results will be added once the runs are complete, and the task suite, results and analysis will continue to be updated on a rolling basis.

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2602.13042

GPTZero: Robust Detection of LLM-Generated Texts

George Alexandru Adam, Alexander Cui, Edwin Thomas, Emily Napier, Nazar Shmatko, Yue Gao, Zikun Chen, Jacob Schnell 等 12 位作者

原文摘要

While historical considerations surrounding text authenticity revolved primarily around plagiarism, the advent of large language models (LLMs) has introduced a new challenge: distinguishing human-authored from AI-generated text. This shift raises significant concerns, including the undermining of skill evaluations, the mass-production of low-quality content, and the proliferation of misinformation. Addressing these issues, we introduce GPTZero 5.0, a state-of-the-art industrial AI detection solution, offering reliable discernment between human and LLM-generated text. Our key contributions include: introducing a hierarchical, multi-task architecture enabling a flexible taxonomy of human and AI texts, setting a new state-of-the-art for AI detection accuracy on 11 independent third-party benchmarks and 18 writing domains, and achieving superior robustness to adversarial attacks and paraphrasing via multi-tiered automated red teaming. GPTZero offers accurate and explainable detection, and educates users on its responsible use, ensuring fair and transparent assessment of text.

cs.LG

版本更新 · v2arXiv:2606.17516

FoundCause: A Foundation Model for Causal Discovery with Latent Confounders from Observational Data

Patrick Blöbaum, Krishnakumar Balasubramanian, Shiva Prasad Kasiviswanathan

原文摘要

Causal discovery from observational data requires recovering directed relations and latent confounding without interventions. We propose FoundCause, an {\em amortized causal discovery foundation model} trained only on synthetic structural causal models that maps datasets to causal graphs in a single forward pass. A permutation-equivariant transformer alternates attention over samples and variables to model cross-variable dependence and per-variable distributions. Pairwise dependence and asymmetry statistics guide its attention, edge decoder and confounder module. The decoder separates edge existence from direction, while triangular refinement incorporates evidence from chains and colliders. Learnable latent tokens predict which variable pairs share a hidden common cause, and a masked input representation handles missing data. To our knowledge, FoundCause is the first amortized causal discovery approach for i.i.d. observational data to predict latent confounding as a separate, explicit output. On 14 real-world and semi-synthetic datasets, FoundCause leads 11 classical and 7 amortized baselines in average AUROC, $F_1$, skeleton $F_1$, and normalized structural Hamming distance ($\mathrm{SHD}/d$): clearly in $\mathrm{SHD}/d$ ($0.875$ vs.\ $0.956$), narrowly in $F_1$ ($0.531$ vs.\ $0.516$). It also has the highest accuracy among amortized methods on bivariate cause--effect pairs.

cs.LG · cs.AI · stat.ME · stat.ML

版本更新 · v2arXiv:2611.16965

Asymptotic Dimension of Persistence Modules of Bounded Presentation

Sushovan Majhi, Atish Mitra, Žiga Virk

原文摘要

We compute the asymptotic dimension of spaces of multiparameter persistence modules of bounded presentation under the interleaving distance. The $d$-parameter modules with at most $n$ generators and $m$ relations have asymptotic dimension, and Assouad-Nagata dimension, exactly $d(n+m)$, the number of coordinates of their generator and relation grades, over every field; for two parameters this is $2(n+m)$. The space has continuous moduli, already for two parameters and $n,m\ge2$: over an infinite field it contains, at every scale, infinite uniformly separated families of pairwise non-isomorphic modules with one fibered barcode, so it is not doubling even at a fixed fibered barcode; already for $m\ge1$ it is not coarsely equivalent to a proper metric space. The proof is an induction on the number of distinct grade coordinates: an interleaving small compared with the gaps between these coordinates moves each of them by at most twice its size and preserves the induced grid representation, so the continuous moduli are invisible at large scale. Each class of modules at finite distance therefore embeds coarsely into Hilbert space; for two parameters, $n,m\ge2$ and an uncountable field, a class containing such a family admits no coarse embedding into a separable Hilbert space. Under the two-parameter matching distance, on the space of rank invariants, the asymptotic dimension and the Assouad-Nagata dimension are again $2(n+m)$: slope-one slices pin the grid of grades, and over a grid only finitely many rank invariants occur; on a finite net of $S$ slices the asymptotic dimension is at most $2nS$.

math.MG · cs.CG · math.AT

版本更新 · v2arXiv:2608.28828

Representation Learning with Quantum Signal Processing

Junqi Wang, Junyu Liu

原文摘要

Representation learning begins when training changes the features that define similarity between data. A frozen-kernel model only reweights a fixed geometry. We establish quantum signal processing (QSP) as a solvable quantum model of the representation-learning regime. At arbitrary depth, we compute the exact mean and variance of its quantum neural tangent kernel, revealing an input-dependent angular geometry whose diagonal remains non-self-averaging even when the underlying unitary approaches Haar randomness. We also prove a sparse-data guarantee for the full nonlinear gradient flow without freezing or ensemble-averaging the kernel: the realized dynamics converges to an integrable scalar flow with a time-dependent kernel closure and explicit convergence times. A finite-depth speed limit holds for every data set and trajectory. At higher data density, numerical results show coupled evolution beyond both the scalar and frozen-kernel descriptions. These results give a controlled theory of learned quantum data geometry with provable training dynamics beyond the frozen limit.

quant-ph · cs.AI · cs.LG · stat.ML

版本更新 · v2arXiv:2510.26185

Cross-Epoch Bias in SGD-based Leave-One-Out Influence: Analysis and Accumulative Correction

Yunxiao Shi, Shuo Yang, Yixin Su, Rui Zhang, Min Xu

原文摘要

Training-data influence estimates support data selection and cleansing by predicting the effects of removing individual examples. The standard multi-epoch SGD-Influence Estimator (SGD-IE) aggregates contributions from a sample's repeated appearances along the recorded trajectory. When used to approximate finite deletion, it omits an interaction: later removals act on the parameter displacement accumulated from earlier removals. We introduce the Accumulative SGD-Influence Estimator (ACC-SGD-IE) to account for how earlier removals change the effect of removing the same sample again. It uses the sample's Hessian at subsequent appearances to correct the estimated parameter change. Our non-convex analysis shows that this correction removes SGD-IE's additional interaction contribution from the finite-horizon error bound: the omitted interaction produces a local error linear in the accumulated parameter change, while the remaining Taylor remainder is bounded quadratically under Lipschitz-Hessian assumptions. The bounds characterize how training propagates the remaining error. In non-convex experiments across clean and noisy tabular, text, and vision datasets, ACC-SGD-IE reduces validation-loss-change RMSE by 10.8% and improves Jaccard@10% by 15.2% on average relative to SGD-IE. These gains also translate into lower test misclassification rates after data cleansing on MNIST and CIFAR10 at the evaluated removal budgets. On noisy industrial datasets, it reduces aggregate parameter RMS error with a mean relative reduction of 53.4%. We further discuss computational tradeoffs, provide complementary theoretical analysis and experimental evaluation for strongly convex objectives, and explore potential extensions of the accumulative correction mechanism to other influence estimators.

cs.LG · cs.AI

版本更新 · v2arXiv:2611.17461

Tracing Knowledge and Reasoning in LLMs

Yang Wang, Xiao Wang, Yiqi Liu, Chenghao Xiao, Eleni Vasilaki, Goran Nenadic, Chenghua Lin

原文摘要

Current evaluations of Large Language Models (LLMs) report performance at the dataset or task level, revealing what a model achieves but offering little insight into the internal processing associated with its performance. We propose a task-centric framework for characterising the model-internal processing elicited by a benchmark. It combines attention- and activation-based signals with representation-based measures to characterise benchmarks spanning a continuum from retrieval-dominant to reasoning-dominant and to surface failure modes that task-level scores conceal. We evaluate 16 LLMs across 24 diverse benchmarks and conduct targeted internal-state analyses on representative models and tasks, observing systematic differences in processing between knowledge-centric and reasoning-centric tasks. We shift evaluation from asking what score a model achieves toward characterising the processing patterns associated with that score, potentially supporting more targeted benchmark selection and more informed model choice. We open source our code at https://github.com/extraordinarylab/trace-kr.

cs.CL

版本更新 · v2arXiv:2609.04747

BEAM3R: Beam's-eye-view architecture with Mamba-3 for implicit dose reconstruction

Chen Cheng, Michael Ferraro, James Grover, David E J Waddington, Emily Hewson

原文摘要

To enable accurate and rapid photon control point and proton beamlet dose calculation in the DoseRAD2026 challenge, we present BEAM3R, a dose estimation framework operating in beam's-eye-view (BEV). Our core innovation combines a Mamba-3 state-space depth-sequence core with physics-based transport conditioning to model long-range depth transport without expensive 3D convolutions. BEAM3R shares a 2D CNN encoder-decoder architecture for photon and proton dose tasks, processing per-plane BEV slices. Proton beamlets are conditioned on water equivalent thickness and remaining range, encoding the parameters determining Bragg peak position. Photon models use a bidirectional Mamba-3 core to capture dose contributions from materials downstream of the calculation point, while the proton model uses a forward core with learned energy-prefix tokens and a Bragg-peak refinement module. To reduce interpolation artifacts and support high spatial resolution, we introduce axial grid alignment of BEV lattices with CT slices and an implicit super-resolution representation arranged as channels, evaluated by a differentiable Triton-accelerated resampler that reconstructs packed cubic B-spline coefficients directly in CT space. For MRI-based tasks, synthetic CTs (sCT) are generated using a conditional GAN with a SwinUNETR generator and a PatchGAN discriminator. On the preliminary DoseRAD2026 test set, CT-to-photon and CT-to-proton models achieved 1%/1 mm local gamma pass rates of 96.8% and 96.0%, with stratified plan-level MAEs of 0.0041 and 0.0079. Substituting sCT reduced gamma pass rates to 89.7% for photon and 75.4% proton plan level doses, with stratified plan-level MAEs of 0.0093 and 0.0336. Standardised runtimes were 23.4 s and 18.4 s for CT-to-photon and CT-to-proton prediction, increasing to 39.7 s and 42.8 s for the corresponding MRI-based pipelines.

physics.med-ph · cs.CV

新论文 · v1arXiv:2611.22009

DiagTrace: An Interactive Benchmark for Clinical Decision Making

Yufan Wang, Rui Yang, Yi Lin, Chunhua Weng, Yifan Peng

原文摘要

Large language models (LLMs) have shown strong performance on medical question answering and diagnostic reasoning benchmarks. However, existing evaluations typically provide all patient information upfront and assess only the final diagnosis or rationale. This setup ignores the need to acquire diagnostic evidence incrementally from incomplete information in real-world diagnosis. To bridge this gap, we introduce DiagTrace, a source-grounded benchmark for evaluating whether LLMs can reconstruct the documented diagnostic trajectory through interactive information seeking. Each benchmark instance is built from a PubMed Central case report and includes an initial presentation, an event bank, a clinical course, and diagnostic references. DiagTrace contains 510 cases across eight specialties, with 225 used to evaluate four LLMs on clinical-course alignment, interaction quality, and efficiency. Results reveal trade-offs in coverage, source-consistent ordering, and turn use.

cs.CL · cs.AI

版本更新 · v2arXiv:2605.09238

iMuon: Intrinsic Spectral Optimization on Riemannian Matrix Manifolds

Yibang Li, Bihari Lal Pandey, Ravi Sah, Andi Han, Cyrus Mostajeran, Pratik Jawanpuria, Bamdev Mishra

原文摘要

Muon and related norm-constrained optimizers, now central to large-scale learning, compute updates via a linear maximization oracle (LMO) over a matrix-norm ball in Euclidean space. However, they do not generalize cleanly to manifold-valued parameters such as low-rank factorizations, orthogonality constraints, or symmetric positive-definite (SPD) matrices. Naively restricting the Muon LMO to the tangent space (i) breaks quotient symmetries and (ii) couples the tangent-space constraint with an ambient norm bound, which obstructs closed-form solutions. We resolve both issues with a key observation: every Riemannian metric canonically lifts a unitarily invariant Euclidean norm to an intrinsic norm on each tangent space. The resulting intrinsic LMO is symmetry preserving and, under a structural condition on the scaled tangent space, reduces to a standard Euclidean LMO. Building on this, we introduce intrinsic Muon (iMuon), a unified framework with closed-form updates on the fixed-rank, SPD, Stiefel, and Grassmann manifolds for various unitarily invariant norms, including the spectral, Frobenius, and nuclear norms. We establish deterministic and stochastic convergence rates of iMuon with constants that depend only on the manifold dimension. Notably, on the fixed-rank manifold, the constant depends only on the rank, which makes the rate independent of factor conditioning and removes the runtime factor rescaling required by prior work. Experiments on LoRA fine-tuning of LLMs, image classification, and subspace learning illustrate the efficacy of the proposed approach.

cs.LG · cs.AI

新论文 · v1arXiv:2611.22006

Supporting Researcher Control in AI-Assisted Social Media Analysis: A Mixed-Methods Study of AI4OSN

Qile Wang, Abhishek Karwankar, Shukria Muhammadi, Srikanth Kumar Perumalla, Abhin Suresh, Sunita Chandrasekaran, Kenneth E. Barner, Matthew Louis Mauriello

原文摘要

High-quality annotated datasets are critical for advancing computational social science (CSS) research, yet collecting, curating, and analyzing large-scale data from dynamic sources such as online social networks (OSNs) remains a persistent bottleneck. Researchers must also translate substantive questions into queries, relevance criteria, and defensible interpretations. Large language models (LLMs) can assist, but they can also obscure the judgments, potentially reducing researcher oversight and critical evaluation. We present AI4OSN, a mixed-initiative platform that keeps researchers in control of data collection, relevance labeling, and sensemaking while making AI assistance available as an inspectable advisory resource. In a systematic user study (N=18) using X/Twitter data, participants reported above-benchmark perceived usability (mean SUS score of 79.7), increased confidence in LLM-assisted annotation and analysis tasks, and low cognitive workload during AI-supported sensemaking. Notably, novice participants showed descriptively greater alignment and higher reported agreement with AI output than experienced participants, underscoring the need to support differentiated verification practices across expertise levels. Overall, this work contributes both a human-centered system for social data analysis and empirical insights into how AI-assisted interfaces shape researcher behavior, trust, and decision-making. Our findings highlight design opportunities and tensions in building accessible, transparent, and agentic AI systems for social media and web research.

cs.HC

新论文 · v1arXiv:2611.22005

Where Should the Lamp Go? Ambient-Aware Lamp Placement for Portraits

Yuyan Chen

原文摘要

Portraits shape first impressions, and lighting is an important factor. Prior work, such as lighting estimation and portrait relighting, edits lighting after capture but does not guide where to place a light before the shot. This leaves an open question: where should a light go to best light a face? Therefore, we propose LightMatch, a preference-grounded inverse lighting framework that disentangles the controllable light from ambient illumination and optimizes its placement. We first learn a Bradley-Terry quality model from pairwise human judgments. A perception head then regresses spherical-harmonic lighting from frozen self-supervised features via cross-attention. Finally, a placement solver isolates the light via spherical-harmonic linearity and optimizes its reachable position. On held-out environments, LightMatch attains 87.8% of the oracle improvement, outperforming the conventional solver that ignores ambient light by a relative 28.4% and the same pipeline with the widely used DPR estimator by a relative 70.5%. It reaches 73.2% on real OLAT faces of unseen identities and, on our real captures, cuts lamp-direction error by 37.7%.

cs.CV · cs.GR

版本更新 · v3arXiv:2604.02203

QuantumXCT: Learning Interaction-Induced State Transformation in Cell-Cell Communication via Quantum Entanglement and Generative Modeling

Selim Romero, Shreyan Gupta, Robert S. Chapkin, James J. Cai

原文摘要

Inferring cell-cell communication (CCC) from single-cell transcriptomic data remains challenging. Most existing methods retrieve curated ligand-receptor pairs, score their coordinated average expression and apply statistical testing, a static and indirect strategy that tends to overlook intracellular signaling consequences, context dependence and higher-order interactions. Here, we introduce QuantumXCT, a hybrid quantum-classical framework that defines CCC as learnable transformations between cellular state distributions induced by cell-cell interaction. By encoding transcriptomic profiles into a high-dimensional Hilbert space, QuantumXCT trains parameterized quantum circuits to learn a unitary transformation mapping a baseline non-interacting cellular state to an interacting state, and infers CCC under explicitly stated modeling assumptions. Unlike methods restricted to curated ligand-receptor pairs, QuantumXCT can evaluate any cross-cell gene pair. On synthetic data with known ground-truth interactions, QuantumXCT ranked the programmed intercellular interactions above non-interacting gene pairs (ROC-AUC 0.93). On an ovarian cancer-fibroblast mono- and co-culture model, it identified a PDGFB-PDGFRB-STAT3 axis reproducible across bootstrap resamples, amplitude encodings and search algorithms, and consistent with published perturbation experiments. The learned circuit is interpretable: its entangling topology translates into interaction networks, and post hoc contribution analysis quantifies the influence of individual interactions on the observed state transitions. QuantumXCT provides an interpretable, hypothesis-generating framework for de novo discovery of communication programs, and delineates both the potential and the current limits of quantum machine learning in single-cell biology.

cs.ET · physics.bio-ph · physics.data-an · q-bio.GN

新论文 · v1arXiv:2611.22000

How Much Distribution Shift Can a Clustering Withstand? Exact Split and Merge Certificates for Structured Transports

Alisina Bayati, Srinivasa Salapaka, Shahriar Talebi

原文摘要

In clustering, the distribution of the population being clustered is often uncertain or changes over time, so the true distribution may shift away from the nominal distribution used to form the clustering. Once the clustering is committed and each member is assigned to a cluster, such shifts may change the distribution of each cluster. They can make a cluster too spread out for one representative at a given resolution, motivating a split, or bring distinct clusters close enough to share a representative at that resolution, motivating a merge. We make these split and merge events precise using a local stability criterion built on the phase-transition analysis in deterministic annealing. This notion of stability enables us to quantify how robust a clustering is against such events. Furthermore, motivated by applications in which uncertainty and population change are structured, we study shifts whose displacements are restricted to a prescribed subspace. The smallest structured shifts that reach the respective thresholds define the split and merge radii, for which we obtain exact semidefinite programming (SDP) reformulations. The split SDP has only two scalar decision variables. These convex reformulations enable us to combine the radii into a robustness certificate for the full clustering that gives the size of the smallest structured shift that reaches any monitored split or merge threshold.

cs.LG

新论文 · v1arXiv:2611.21998

KV-LTM: Persistent Per-Session KV Caches as Long-Term Memory for Personal Assistants

Ziv Kfir, Ido Kfir

原文摘要

Personal assistants accumulate months of conversations, but today's long-term memory stacks put derivation or selection between a question and its evidence. In a system-level comparison on LongMemEval, two commercial assistants scored well below the same model reading the history offline [1], consistent with, but not isolating, content loss between write and read. We propose KV-LTM: a memory tier storing each session's raw text plus its KV cache under a fixed reader model, answering by restoring cached sessions and appending the question. KV-LTM is complementary to, not a replacement for, retrieval and indexing. Text is the memory of record; the cache is a recompute-free prefill accelerator, degrading gracefully to text. We specify the design: storage record, budget-derived retention, append-only read path, and bounded aggregation. We size it analytically: across pinned BF16 full-attention (GQA) and latent-cached MLA configurations, per-token state spans approximately 31K-328K bytes (the pinned KDA+MLA hybrid differs: approximately 8.1K bytes/token plus a fixed per-session recurrent term), giving approximately 0.34-3.6 TB per user-year at a declared 30K-token/day scenario, against approximately 49 MB of raw text; per-query cost is modelled as regime-conditional transfer, attention, decode, aggregation, and compute. We define an evaluation protocol needing no persistent-cache implementation for logical QA evaluation: per-session prefill emulates valid cache reuse under the same model/input-state contract and ideal arithmetic, with named arms, controlled baselines, and a preregistered reader-model gate; a separate minimal real-cache replay tests numerical equivalence and measures the cost axis, with outcomes not assumed. KV-LTM trades storage for avoided re-prefill compute and write-time fidelity, within a declared retention budget.

cs.AI

新论文 · v1arXiv:2611.21996

Beyond Appearance: Where Forest Visual Place Recognition Actually Fails

Blake Matheson, Ben McShanag, Isabella Moffat, Michael Milford, Peyman Moghadam, Dana Kulić, Somayeh Hussaini, Kavindie Katuwandeniya

原文摘要

Visual place recognition (VPR) in forest environments remains challenging because repetitive vegetation, and changes in illumination, season, and viewpoint can make distinct places appear similar and revisited places appear substantially different. In this paper, we investigate whether temporal, linguistic, structural, and geometric context can improve on an appearance-only descriptor, and what limits each representation when it does not. Using MegaLoc as the appearance-based baseline on the WildCross benchmark, we evaluate score-space and descriptor-space sequence matching, vision-language captions and reranking, scene-graph representations, and depth-derived stem graphs across same-direction revisits, extended routes, and reverse traversals. On a same-direction revisit, both sequence matching strategies reach similar Recall@1 (94.1% vs. 91.5%), but recall at 100% precision rises from 50.9% (single-frame MegaLoc) to 71.6% in score space and falls to 36.5% in descriptor space. The remaining context representations provide no consistent improvement over the appearance-based baseline. Same-place captions show limited place-specific discrimination, reranking is constrained by the initial candidate shortlist, and stem-graph matching remains weak even with LiDAR depth.

cs.CV

新论文 · v1arXiv:2611.21993

DEFTS: Data-Efficient, Training-Free Few-Shot Learning for CLIP in the Text Subspace

Yijin Zeng

原文摘要

Contrastive Language-Image Pre-training (CLIP) achieves impressive zero-shot image classification performance by comparing image embeddings against class-specific text embeddings. While recent few-shot methods leverage labeled training samples to improve upon this zero-shot baseline, they often predominantly rely on image embeddings and underutilize the semantic structure of the text embeddings. In this paper, we introduce DEFTS, a data-efficient, training-free few-shot classification method strictly in the text subspace. We first demonstrate empirically that while raw text embeddings can be suboptimal as direct classifiers, the linear subspace they span remains highly discriminative. DEFTS therefore proposes to reduce the image-text modality gap by projecting estimated image prototypes directly into this subspace. Importantly, by expressing these prototypes as linear combinations of text embeddings, DEFTS reduces a high-dimensional estimation problem to the derivation of just a few coefficients. These coefficients are then computed via a Bayesian posterior mean, using a prior naturally centered on the original text embedding coordinates. Extensive experiments across 12 image classification benchmarks demonstrate that DEFTS significantly improves upon existing training-free methods.

cs.CV · stat.ML

新论文 · v1arXiv:2611.21983

Large Language Models as Nonlinear Dynamical Systems: The Three Clocks of Depth, Training, and Generation

Maor Farid

原文摘要

Language models are dynamical systems. A transformer is iterated over its layers, over the steps of its training and over the tokens it generates, and on each of these three clocks it shows behavior that nonlinear dynamics has studied for a century: fixed points, bifurcations, synchronization, chaos and noise-driven escape from potential wells. The two communities rarely meet, so this behavior is often rediscovered under new names. We build a bridge between them. To describe, we condense about 200 papers into the Three-Clock Dictionary, which maps fifteen concepts of nonlinear dynamics onto each clock and marks every correspondence as proved, measured or conjectured, and we show each concept in a mechanical system and in a language model side by side. To explain, we derive reduced-order models: the softmax is a Boltzmann distribution, gradient descent an Euler step on a nonlinear spring, a loss spike a ball thrown out of a stiff valley, attention on the circle a Kuramoto model, and a repetition loop a well that deepens while it is occupied. We then test these explanations on open language models, on a laptop CPU. Escape from repetition loops in GPT-2 and Pythia follows the Arrhenius law with the logit gap as the barrier, and the barrier deepens and then saturates, so the temperature needed to leave a loop falls like $1/\ln N$ with the generation length $N$ and rises with model size. Coherent text lives in a narrow window of temperatures, which a small reasoning model shares at its recommended temperature. Training makes each Pythia layer more expansive, and a small transformer trains at a multi-mode edge of stability. The third step, solving problems of language models, is still ahead: controllers derived from the escape analysis remove loops but do not yet beat the best fixed temperature. We state twelve open problems where nonlinear dynamics could get there.

cs.LG · cs.CL · math.DS · nlin.CD