跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1112新增论文
+875其中 AI 相关
+133已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 20:16 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 20:18 — 2026-11-19 20:18(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-19 20:16最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 02:59

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

27,982 已收录论文23,249 AI 相关8,559 有修订112 HF 社区发现

浏览论文库

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

找到 54 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 20:10(北京时间)
新论文 · v1arXiv:2611.22595

Lost in the Funnel: Selection-Induced Miscalibration in Ranking and Decision Systems

Aditya Somani, Rahul Ragesh, Vikas Joshi, Amit Singh

原文摘要

Modern ranking and decision systems combine components with divergent objectives, and scores calibrated at the model boundary are used as calibrated probabilities throughout the funnel, across filtering, reranking, business-rule enforcement, and auctions. Yet calibration is typically validated only where the score is produced, so its breakdown where the score is used is routinely overlooked. We ask when calibration survives this selection, how inherited error differs from selection effects, and what can fail for a perfectly calibrated score at a component boundary. We study these questions through a boundary-wise diagnostic framework of residual identities. We target rubric-judged relevance rather than presentation-dependent metrics such as CTR, so calibration is measurable at every funnel layer of interest. We first present an industry-wide case study that applies our diagnosis to settings where calibration deteriorates at decision time, tracing the degradation to selection rather than model error. This diagnosis motivates Funnel-Aware Recalibration (FAR): post-hoc, selection-policy-aware recalibration at the boundary where scores drive decisions. In a live two-region production A/B test, FAR cuts decision-time expected calibration error (ECE) by 60-80% and improves auction efficiency. We further adapt two public datasets to simulate industry settings, providing additional evidence for the mechanism. We plan to release the adapted datasets and their generation pipeline to support further research. Finally, we distill these findings into practical operating principles for calibrating multi-stage scoring systems.

cs.LG

新论文 · v1arXiv:2611.22064

Data-Efficient Algal Bloom Segmentation in Freshwater Bodies Using a Three-Stage Transfer Learning Pipeline with Attention-Enhanced Decoding

Albert Ansah Benson, Mingqiang Han, Rahul Harsha Cheppally, Treman Singh Kaloya, Menard Soni, Sudan Baral

原文摘要

Harmful algal blooms threaten water quality and public health, yet automated segmentation of bloom regions in freshwater imagery is limited by scarce pixel-level annotations. We present a transfer-learning pipeline that adapts a Swin Transformer U-Net with SCSE decoder attention from ImageNet-1K to water-body segmentation (RIWA, LaRS) and then to algal blooms, together with a model-assisted annotation protocol that expands the labelled algae corpus from 145 to 655 images. In a single-seed ablation on a 41-image validation split (checkpoint S2-A4 and its variants), corpus expansion is the dominant factor (+11 mIoU points); water-body pretraining helps only on the expanded corpus (+1.1 points over ImageNet initialization); SCSE attention adds 0.3 points; and a learnable positional encoding lowers mIoU by 0.6 points and is omitted. Adding 476 images, 188 of them algae-free, reduces false-positive area on non-water scenes from 22.6% to 4.9%. Against nine baselines on a 256-image test split, a separately trained checkpoint of the same architecture (S2-A13) reaches mIoU 0.919 and the highest algae IoU (0.902); a near-duplicate audit indicates train/test overlap in this split, so these scores are likely optimistic.

cs.CV

新论文 · v1arXiv:2611.21206

PQC Migration: End-to-End Performance Profiling of Post Quantum Cryptographic Algorithms in mTLS

Rahul, Manjesh K. Hanawal, Sameer G. Kulkarni, Saravanan V, K. Tirumaleswar Reddy

原文摘要

Emerging quantum computers threaten to break the classical key exchange algorithms. To safeguard against these threats, migration to new quantum-safe algorithms is underway and expected to be expedited. Though resistant to attacks, the quantum safe algorithms may impact the real-world performance due to their large key lengths. In this work, we analyze the end-to-end performance of the Transport Layer Security (TLS) protocol with the post-quantum (PQ) and hybrid cryptographic algorithms standardized by NIST. We develop a test setup to evaluate the performance of TLS connections between a client and a server under various network conditions. We focus on the impact of the new algorithms on the speed (throughput, connection time) and sustainability (energy, CPU cycles) of TLS 1.3. Our analysis demonstrates that the standardized post-quantum algorithms do not introduce any measurable performance degradations in TLS 1.3, despite their larger key lengths. However, hybrid algorithms introduce noticeable performance degradation, which becomes increasingly pronounced under adverse network conditions. Our analysis suggests that migration to hybrid algorithms should be ``network condition aware'' as poor network conditions can severely degrade performance in TLS 1.3. We provide anonymised link to the code and a web interface to analyse performance of various combination of algorithms.

cs.CR

新论文 · v1arXiv:2611.20969

AutoDiDact: Input Reduction over Inferred Structure

Aarush Kumbhakern, Rahul Gopinath

原文摘要

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

cs.SE

新论文 · v1arXiv:2611.20797

Correspondence-Free Camera Pose Estimation by Matching Moments

Subhransu S. Bhattacharjee, Dylan Campbell, Rahul Shome

原文摘要

The blind perspective-$n$-point (PnP) problem is to estimate the pose of a calibrated camera from 2D and 3D point sets with unknown correspondences. We show that, for complete, noiseless observations, fourteen permutation-invariant image moments up to order four identify a fixed camera pose for almost every 3D point set containing at least twenty points. Our learning-free method, MomentPnP, matches these moments between the observed 2D points and the projected 3D points to initialize a camera pose without correspondences and refines the pose and correspondence weights using expectation--maximization. Across the test sets of three benchmarks, our method reduces median rotation error by $5$--$170\times$ relative to the best learned baseline, both with and without outliers. We recover accurate poses even with as many outliers as inliers. On dense ETH3D scans, pose accuracy improves as the point sets grow, even as individual correspondences become harder to resolve.

cs.CV · cs.LG · cs.RO · eess.IV · math.OC

新论文 · v1arXiv:2611.20095

High-Throughput Serving of Nemotron 3.5 Transcribe with Regime-Aware Megakernels and Kernel Fusion

Aditya Chatterjee, Sanjay Singh Chauhan, Mayank Jain, Arushi Dhingra, Sahin Chowdhury, Rahul Mittal

原文摘要

Nemotron 3.5 Transcribe ranks first among open-weight models on the Hugging Face Open ASR leaderboards. Serving it efficiently takes more than fast operators: continuous batching changes the amount and mix of work at every iteration, and the best fusion granularity changes with it. We present a serving engine that, for every pass, chooses between persistent megakernels and chains of fused kernels at crossovers measured offline. On an H100 SXM GPU, throughput of our accuracy-preserving serving peaks at 4,345x real time, 1.39x the peak of tuned vLLM, and is up to 4.39x faster at low concurrency; on B200 it peaks at 6,367x, 1.64x vLLM at the highest concurrency we measured. Word error rate (WER) is 1.91 to 1.93% against 1.88 to 1.93% for vLLM. Within a 400 ms budget for p95 end-to-end completion time, it serves 8x as many concurrent requests. Choosing per pass beats either level alone: 23% higher throughput than always using megakernels at 128 concurrent requests, and 9% higher than always using fused kernels at 8. Opt-in switches, including greedy MoE layer skipping, add 13 to 16% throughput on B200 for offline jobs that can accept higher WER.

cs.PF · cs.DC · cs.LG · eess.AS

新论文 · v1arXiv:2611.19730

AlphaTruck: A Platform for High-Speed Off-Road Autonomy on Unstructured Terrain

Rwik Rana, Adam J. Thorpe, Jesse Quattrociocchi, William Ward, Goktug Poyrazoglu, Adam Uccello, Christian Ellis, Rahul Moorthy Mahesh 等 14 位作者

原文摘要

Progress in autonomous navigation in off-road environments requires not only advances in algorithms, but also robust and capable physical platforms suited to both development and deployment. Today, off-road autonomy is typically developed and tested at one of two extremes of vehicle scale, each with different drawbacks. Full-size vehicles are capable but expensive, require large logistic infrastructure for deployment and maintenance, and expensive when pushed beyond their limits. RC-scale vehicles are small and inexpensive, but limited in the terrain they can traverse and the payload that they can carry, which includes their sensors and compute. We present the AlphaTruck platform, which leverages recent advances in compact sensing and compute to integrate multimodal sensing, embedded CPU-GPU compute, and an onboard autonomy stack for high-speed, off-road navigation, all integrated into a large-scale, 1/5th RC vehicle chassis. AlphaTruck is designed as both a research testbed and a field-deployable platform for commercial and defense missions such as survey, search and rescue, and agriculture, with the capacity to carry task-specific payloads. At 1/5 scale, the autonomy stack, sensors, and batteries all compete for the same mass, power, and cooling budget, so the platform must balance five needs: mobility over rough terrain, rich sensing, onboard computation, payload capacity to carry the autonomy stack while leaving room for task-specific equipment, and practical operation and repair. Thus, AlphaTruck navigates off-road environments autonomously at 6-10 m/s using only onboard sensing and compute.

cs.RO

新论文 · v1arXiv:2611.19719

Found, but Not Fixed : From Software Vulnerability Discovery to Fixes with Iterative LLM Pipelines

Youssef Gamal, Mohamad Fakih, Halima Bouzidi, Rahul Dharmaji, Gustavo Quiros Araya, Oluwatosin Ogundare, Mst Ayesha Siddika, Mohammad Abdullah Al Faruque

原文摘要

Software vulnerabilities persist as a critical threat despite the deployment of sophisticated detection tools and AI assistants. While detection has advanced, the subsequent code repair phase remains a primary bottleneck; manual intervention is inherently slow, costly, and prone to introducing secondary regressions and issues. In this paper, we investigate whether an iterative, LLM-based pipeline can provide a robust solution for the automated repair of vulnerable functions in real-world code. We propose a generalized framework that leverages the reasoning capabilities of Large Language Models (LLMs) through a multi-stage feedback loop. We benchmark this approach against state-of-the-art models, including GPT-4o, GPT-5.1, and Gemini 3 Flash, demonstrating that such a pipeline can achieve high-quality code repair. To support the broader security community, we provide our evaluation framework, fine-tuned weights, and comprehensive experimental dataset on our website: https://sites.google.com/view/llm4cve

cs.SE · cs.CR · cs.LG

新论文 · v1arXiv:2611.17541

Quantum Algorithm with Quadratic Speedup for 2D Pattern Matching

Rishabh Gala, Rahul Shah

原文摘要

We consider the problem of 2 dimensional pattern matching under Quantum Query model. Here, we are given a rectangular text $T[0..n_1-1][0..n_2-1]$ and a pattern $P[0..m_1 -1][0..m_2-1]$. We take $N = n_1n_2$ and $M = m_1m_2$ as the sizes of text and the pattern respectively (we assume $M < N$). Based upon the Quantum Advantage given by Grover's search (and subsequent Dürr-Høyer search), we create a solution which takes $\tilde{O}(\sqrt{N})$ query complexity to answer if the pattern $P$ exists in $T$. Our solution uses deterministic sampling as a primary component. As noted by earlier work in the literature, deterministic sampling is inadequate and witness tables are essential components for 2D matching. In our settings, we assume that the witness table of the pattern is precomputed classically and is available as an oracle to the quantum algorithm. Our main novel component is how to compute and employ a geometric structure called ``skyline" without losing the quantum advantage.

cs.DS

版本更新 · v2arXiv:2611.10224

Jais 3: Introducing Arabic-centric Agentic AI

Team IFM, Haonan Li, Hadi Abdine, Nikhil Ranjan, Mohamed Anwar, Ahmad Chamma, Amr Mohamed, Ahmed Frikha 等 54 位作者

原文摘要

We present Jais 3, a fleet of six open, Arabic-centric agentic language models ranging from 0.9B to 375B parameters. Jais 3 is built to complete tasks for Arabic speakers, not only to answer questions in plain text: it is trained to plan multi-step tasks, call tools and Model Context Protocol (MCP) servers, operate a terminal, search the web, and read, edit, and produce PDF, spreadsheet, and presentation files, while communicating with the user in Arabic. Instead of pretraining from scratch, we adapt each model of the fully open K2 Horizon fleet to Arabic through continual pretraining, followed by supervised fine-tuning (SFT), final token preference optimization (FTPO), and reinforcement learning with verifiable rewards (RLVR). We combine natural Arabic text with translated, transliterated, and synthetic Arabic, and replay the base model's own training data to keep its reasoning, agentic, and English abilities. Jais 3 covers Modern Standard Arabic and the major regional dialects, follows instructions with Arabic-specific constraints, and inherits the 512K-token context window of K2 Horizon (all models except the 0.9B). To our knowledge, its 375B model is the largest open Arabic-centric language model to date. For evaluation, we revisit how Arabic models are assessed, moving to fully generative evaluation on audited Arabic benchmarks. Across model sizes, Jais 3 matches or outperforms open-weight models of comparable size on Arabic and agentic benchmarks, with particularly strong agentic capabilities and Arabic instruction following, and far fewer hallucinations. We release the weights and the checkpoints from every training stage of all six models, together with samples of the training data, the data recipes and training configurations, the training logs, the audited benchmarks, and the evaluation code.

cs.CL · cs.AI

新论文 · v1arXiv:2611.15718

Orbit: An Evidence-Grounded Benchmark for Evaluating LLMs on IT Operations Reasoning

Sathwik Narkedimilli, Rakshit Verma, Rahul Soni, Ankit Kushwaha, Balaji Ganesan, Kaustabha Ray, Sunil Saumya, Pratibha Moogi

原文摘要

LLMs now support IT operations (ITOps), but benchmarks rarely show why a model fails. We present ORBIT, a benchmark of ITOps questions in three formats, namely multiple-choice, open-ended, and troubleshooting, with each question accompanied by a reference answer and a recorded source. An audit found template defects in about a tenth of the generated items, so we drop them and rebuild the troubleshooting format from real practitioner threads with accepted answers. Under one independent judge, five LLMs answer most multiple-choice items correctly, between a third and just over half of the open-ended items, and a minority of the troubleshooting items, even under a more lenient root-cause rubric. When models judged their own answers, they accepted many answers to defective items, so we use one independent judge for every model. Word overlap with the question finds the correct option for more than half of the multiple-choice items. ORBIT is a diagnostic aid for selecting and supervising assistants rather than a deployment test.

cs.LG · cs.SE

新论文 · v1arXiv:2611.15710

Curiosity-0826-4B: Generative Medical Event Sequence Modeling Across Pediatric and Adult Populations

Mani Nagarathnam, Luke Benham, Paul Blazek, John Cashy, Kevin Chung, John Muenning, Hank Voeller, Shane Waxler 等 17 位作者

原文摘要

We introduce Curiosity-0826-4B, an updated version of the generative medical event foundation model trained on Epic Cosmos that simulates patient timelines to produce zero-shot clinical predictions. Curiosity-0826-4B incorporates a broader patient population and richer clinical event representations, while generally matching or exceeding Curiosity-0226-1B, the largest model in the previous Curiosity-0226 series, on evaluated tasks supported by both models. Laboratory value prediction improved, with MAE 18--46% lower than that of Curiosity-0226-1B. We evaluated prediction of disease events across pediatric cohorts aged 2--17 years. AUROCs for new asthma diagnosis (0.742--0.785) and asthma exacerbation (0.829--0.852) were comparable to those in the adult reference cohort, while AUROCs for sickle cell crisis (0.820--0.847) were lower than in adults (0.915). Explicit representation of documented death enabled new mortality prediction tasks among adults across hospice, inpatient, and ambulatory settings (AUROC 0.821--0.942). Scaling-law analysis guided compute-optimal initial pretraining followed by continued pretraining with context extension. The resulting Curiosity-0826-4B model has more parameters (4.3B versus 1B) and a longer context window (16K versus 8K). It processes 56% fewer training tokens and requires 2.2 times the training floating point operations (FLOPs) compared with its predecessor. By extending a common zero-shot prediction strategy to pediatric patients and additional outcomes, Curiosity-0826-4B broadens opportunities to develop clinical and operational applications without training separate task-specific models. Further validation should assess local calibration, performance across patient subgroups and event frequencies, timeline completion rates, and generalization to new settings, alongside prospective evaluation of clinical and operational utility.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.13846

Optimal Last-Iterate Bounds for Nonexpansive Stochastic Approximation

Ramanan Tamizholi, Siddharth Chandak, Rahul Singh

原文摘要

We establish last-iterate mean-square residual bounds for nonexpansive stochastic approximation (SA), or stochastic Krasnoselskii-Mann (KM) iterations. In particular, we consider fixed-point mappings that are nonexpansive with respect to the Euclidean norm, and focus on polynomially decaying stepsizes. We study three conditions on the conditional second moment of the noise, and obtain bounds that are optimal up to logarithmic factors in each case. When it scales linearly with the squared residual, the best rate is $O(1/k^{1-ε})$ for any $ε>0$. In this case, for all considered stepsizes, our bounds match those of the noiseless KM iteration. When it is bounded by a constant, the best rate is $O(\log^2 k/\sqrt{k})$. When it scales affinely with the squared norm of the iterate, the best rate is $O(1/k^{1/2-ε})$, and the mean-square residual can diverge if the stepsizes are not square-summable. Thus, unlike for contractive SA, square-summable stepsizes are necessary for nonexpansive SA. We demonstrate how various algorithms with cocoercive maps, such as stochastic gradient descent, linear SA, and learning in cocoercive games, fit into our framework, and how the different noise conditions arise in each of them.

math.OC · cs.LG · eess.SY

版本更新 · v2arXiv:2611.09964

How Many Demonstrations Does a VLA Need? On the Sample Efficiency of VLA Finetuning

Rahul Chand, Miguel Villa Floran

原文摘要

Pretrained vision language action (VLA) models show strong zero-shot performance but they are rarely deployed directly and are often first post-trained on demonstrations from the target setting. Yet VLAs are typically compared by zero-shot or full-data fine-tuned success which reveals little about the data and compute required for downstream adaptation. We study adaptation efficiency for six VLAs ($π_0$, $π_{0.5}$, and GR00T N1-N1.7) on four LIBERO suites, varying both demonstrations and training steps. This reveals differences hidden by full-data fine-tuning: models which are within two points on the full LIBERO-Spatial dataset differ by up to 3$\times$ in success with 50 demonstrations. $π_{0.5}$ needs 2-5$\times$ fewer demonstrations than $π_0$ and is the most sample-efficient model at every budget, with the largest gap on the long-horizon suite. Within GR00T, N1.5 adapts more efficiently than N1.6 and N1.7 on three of four suites, despite their stronger zero-shot performance. We also study one pretraining factor behind these differences by freezing the VLM during finetuning: this severely degrades the $π$ models whose VLM is jointly trained with the action expert during pretraining, but barely affects GR00T models.

cs.CV · cs.RO

新论文 · v1arXiv:2611.12422

Two-Phase Rapid Simulation-Based Inference with Differentiable Simulators

Uros Zivanovic, Rahul Srinivasan, Roberto Trotta, Andre Scaffidi

原文摘要

We introduce Rapid Simulation Based Inference (RSBI), a diffusion-based variational approach to likelihood-free Bayesian inference that achieves high sampling efficiency under large prior-to-posterior volumes. RSBI builds on advances in Schrödinger Bridge (SB) diffusion sampling to handle multi-modal posteriors, with an initial likelihood supplied by a distance measure via a differentiable simulator. The key innovation of this initial surrogate likelihood is that it gives a highly efficient proposal distribution, replacing sequential rounds of other methods with an efficient one-shot proposal. Subsequent refinement then transports the proposal to the true posterior as specified by the simulator and the original prior. The SB sampler is warm-started from the proposal, and its energy is corrected by a neural likelihood ratio that is learned only where the proposal places mass. As a variational method, RSBI does not suffer from prior leakage commonly observed in standard sequential posterior estimation methods. To improve mode coverage we optionally utilize the well-tempered meta-dynamics framework, which also encourages exploration of the prior volume. We observe strong performance on standard SBI benchmarks, particularly when the prior volume is increased relative to the ground truth posterior, achieving a performance degradation of only $\sim5\%$ on Two Moons under a highly constrained simulation budget. Additionally, we evaluate RSBI's performance for gravitational wave ring-down posterior estimation, in a real-world physics benchmark inspired by black hole spectroscopy.

cs.LG · stat.ML

版本更新 · v3arXiv:2310.11531

Informed Posterior Sampling: More Efficient Online Learning with Few Offline Demonstrations in Average-Reward MDPs

Dengwang Tang, Dongze Ye, Botao Hao, Rahul Jain, Zheng Wen

原文摘要

We study efficient online reinforcement learning in the infinite horizon setting when there is an offline dataset to start with. We assume that the offline dataset is generated by an expert but with an unknown level of competence, i.e., it is not perfect and not necessarily using the optimal policy. We show that if the learning agent models the behavioral policy (parameterized by a competence parameter) used by the expert, it can do substantially better in terms of minimizing cumulative regret than if it does not do that. We establish an upper bound on regret of the exact informed PSRL (iPSRL) algorithm that scales as $\widetilde{\mathcal{O}}(\sqrt{T})$. This requires a novel prior-dependent regret analysis of Bayesian online learning algorithms for the infinite horizon setting. We then propose the informed RLSVI (iRLSVI) algorithm to efficiently approximate the iPSRL algorithm. Empirical results show that small offline expert datasets are sufficient for iRLSVI to outperform online-only algorithms on hard exploration domains.

cs.LG · cs.AI · eess.SY · stat.ML

新论文 · v1arXiv:2611.11197

Dhara: Evidence-Oriented Retrieval for Indian Knowledge Systems

Avinash Holenarasipur Nagendra, Anand Kaniyaar Sriranga Prasad, Rahul Vishwakarma, Trupti Gavit, Anish Amol Tipnis, Yashaswini Mandayam Rangayyan, Vinod Appajanna, Kousik Sarathy Sridharan 等 9 位作者

原文摘要

Relevant evidence in Indian Knowledge Systems (IKS) collections may be distributed across passages in different parts of a work, including verses, translations, and commentaries. Locating it requires matching natural-language questions and partially remembered verse fragments to source passages. We present Dhara, a retrieval engine combining hybrid search, chapter- and book-level Entity Notes (EN), Fuzzy Verse Retrieval (FVR), and neural reranking. Five comparisons on the 325 questions in Dhara Bench examine retrieval representations against BM25, EN's contribution, reranker quality and computation time, FVR, and Gemini. BGE-M3 single-vector retrieval exceeds BM25 in nDCG@10, Recall@20, and MRR@20 across all categories. Its scores are broadly comparable to ColBERTv2, with mean retrieval times of 0.108 s and 0.962 s under the same hardware configuration and a smaller memory footprint for chunk storage on disk. Adding EN to a direct branch with a matched candidate count improves nDCG@10 in all twelve categories with Qwen and ten with BGE; the combined ranking is capped at the same candidate count. Qwen improves nDCG@10, Precision@5, and MRR@20 over BGE in every category, at approximately 6.72 times the overall estimated serial computation time. FVR increases Verse-category nDCG@10 by approximately 20 percentage points with either reranker. Gemini is evaluated after source mapping and manual review with relevance annotations visible. The Qwen pipeline with EN and FVR has higher Recall@20 than Gemini in ten categories and stronger complete-evidence retrieval in Multi-hop questions, while Gemini retains early-relevance advantages in several categories. The results inform retrieval choices according to evidence requirements and resource budgets.

cs.IR · cs.CL

版本更新 · v2arXiv:2610.22852

Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors

Carl Qi, Weijun Dong, Xiaojie Wang, Peiyi Chen, Rahul Sajnani, Mingyuan Zhang, Amy Zhang, Jose Barreiros 等 11 位作者

原文摘要

Generalist robot policies offer strong behavioral priors, but achieving deployment-level reliability and throughput remains difficult. Reinforcement learning (RL) can improve these policies, yet its effectiveness is constrained by the cost of online interaction. Existing methods adapt frozen flow-matching policies by treating noise space as a continuous action space. We show that this behaviorally unstructured space makes exploration inefficient, often preventing these methods from extracting meaningful learning signals on challenging tasks. We introduce AnchorQ, which enables coarse-to-fine policy improvement through a structured, refinable latent action representation. At each decision step, AnchorQ uses flow reversal to map reference behaviors to state-conditioned latent anchors, samples local particles around those anchors, and applies value-guided sampling to explore promising refinements. Our analysis shows that anchors reduce identification complexity at the cost of support bias; particle refinement trades this bias against action-class complexity; and critic accuracy determines the reliability of KL-regularized, value-guided selection. Across simulated and real-world manipulation tasks, AnchorQ outperforms state-of-the-art post-training baselines in sample efficiency, delivering a 37% improvement in real-world success rate and 97% higher simulated task throughput under the same interaction budget. Additional visualizations are available on our website https://anchorq-rl.com/.

cs.RO · cs.AI

新论文 · v1arXiv:2611.10961

Improving Analytic Constants via Interpretable AI-Guided Lean Proof Refinement

Rahul Saha, Alan Li, Anton Xue, Swarat Chaudhuri, Adam Klivans, Pravesh K. Kothari, Raghu Meka

原文摘要

AI agents are increasingly capable of discovering new mathematical results, yet their reasoning and generated proofs can be difficult to understand and verify. We introduce an interpretable framework for AI-guided mathematical discovery, focused on improving quantitative bounds on analytic constants. Our key insight is that existing proofs often contain slack in intermediate lemmas, which can be tightened without reconstructing the entire argument. To exploit this structure, we represent proofs as partially-formalized Lean blueprints: human-interpretable dependency graphs of definitions, lemmas, and theorems. An AI agent then iteratively refines the Lean code while preserving the blueprint's dependency structure, allowing local improvements to automatically propagate to a verified final bound. This interpretable structure allows humans to inspect the agent's refinements and understand how local improvements propagate to the final theorem. For Grothendieck's constant ($\mathcal{K}_G$), we obtain $$ \mathcal{K}_G \leq \fracπ{2\log(1+\sqrt{2})} - 10^{-17}, $$ an explicit numerical improvement over Krivine's 1977 bound. For Korenblum's constant ($\mathcal{K}_K$), we obtain $$ \mathcal{K}_K \geq 0.356565, $$ improving Wang's 2025 bound of $0.3554$. Our experiments demonstrate the potential of both partial formalization and iterative agentic refinement for interpretable mathematical discovery.

cs.AI · cs.LG · math.NA

新论文 · v1arXiv:2611.10926

DeepFinance: Can AI Diligence a $100MM Deal?

Drew Hahn, Tyler Shibata, Jackson Grove, Rahul Sonwalkar

原文摘要

Existing evaluations of AI models on high-finance work focus on retrieving answers from financial documents and producing numerically correct outputs. Real private equity (PE) and investment banking (IB) work also depends on choosing between conflicting sources, making sound assumptions, and keeping every step auditable. We introduce DeepFinance, an ultra long-horizon benchmark of 21 end-to-end PE and IB tasks that take a human professional an average of 27.1 hours. Each task pairs a request with a data room averaging 19 files and is graded against an average of 84 expert-written rubric criteria covering output, workflow, and judgment. We evaluate 22 model configurations, each in its native agent harness. The best configuration, GPT-6 Astra with max reasoning, satisfies 57.6% of rubric criteria, and the top four configurations are not statistically distinguishable. Frontier models often calculate correctly from the wrong inputs and find decision-relevant evidence without acting on it.

cs.CL · cs.AI · q-fin.GN

版本更新 · v2arXiv:2606.13825

Scalable Deep Unfolding of Conic Optimizers

Alex Oshin, Rahul Vodeb Ghosh, Evangelos A. Theodorou

原文摘要

Deep unfolding (DU) accelerates iterative optimizers by training learnable components through unrolled iterations, but extending DU to the large-scale semidefinite programs (SDPs) common in robotics has remained limited. Unrolling a full-update conic solver such as COSMO exposes two obstacles: backpropagating through the per-iteration linear-system solve incurs memory quadratic in the problem size when the coefficient matrix is formed explicitly, and backpropagating through the positive semidefinite (PSD) cone projection is numerically unstable under repeated eigenvalues. We address the first with a matrix-free implicit differentiation rule that reduces memory from $O(n^2)$ to $O(n + \mathrm{nnz}(A))$, and the second with a stable backward rule based on the Dalečkii--Krein representation of the Fréchet derivative. Together, these enable learning lightweight hyperparameter policies and warm starts for COSMO. On standalone SDPs and second-order cone programs, ranging from max-cut and Lovász $\vartheta$ to robust estimation and control, the learned policies outperform tuned COSMO on every problem class, reducing iterations to tolerance by up to 60$\times$, and transfer without retraining to instances up to 10$\times$ larger in the size parameter while retaining 2--5$\times$ speedups. Our matrix-free solver implementation also batches naturally on the GPU, solving 64 Lovász $\vartheta$ SDPs 14$\times$ faster than sequential COSMO.jl. When embedded in sequential convex programming for nonlinear covariance steering, our learned optimizers outperform the interior-point solver Clarabel in terms of both success rate and solve time.

math.OC · cs.LG

版本更新 · v2arXiv:2605.22897

From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data

Mohammad R. Rezaei, Rahul G. Krishnan

原文摘要

When software fails, we read the error, form a hypothesis, write a patch, and test it. LLMs now do this for neural networks by editing weights; when a tabular model fails, we usually retune it. Most interpretability methods report which features matter rather than how they combine. Rather than asking an LLM to predict the target over the whole output space, we anchor the prediction with a base model and ask the LLM to debug it. We introduce Multi-Agent Residual In-Context Learning (MARICL), in which LLM agents read high-residual examples, hypothesize the missing structure, and write executable correction terms that are then refined by multi-turn textual gradient optimization. The resulting corrections are readable, executable hypotheses about what the base model misses, rather than validated mechanisms. Across nine benchmarks covering scientific, biomedical, socioeconomic, and synthetic data, MARICL reliably repairs its base model's structured residuals, improving it on every dataset, and on synthetic data absent from pretraining it recovers the hidden structure (two seeds). Against the strongest competing baseline it leads on five of the eight real benchmarks and trails TabPFN on the other three, while adding an inspectable correction that black-box baselines do not provide. Code is available at https://github.com/MrRezaeiUofT/Multi_Agent_Residual_In_Context_Learning.

cs.LG

版本更新 · v3arXiv:2606.05487

VASTO: Simultaneous reconstruction of vascular geometry and blood flow from tomographic projections via differentiable topology optimization

Pramod Thombre, Rahul Kumar Padhy, Roshan M. D'Souza, Krishnan Suresh

原文摘要

Computed Tomography Angiography (CTA) is widely used to reconstruct vascular geometry from projection measurements, with conventional approaches such as Filtered Back-Projection (FBP) and Iterative Reconstruction (IR) forming the clinical standard. Despite recent advances, these methods remain susceptible to sparse and noisy measurement, making accurate recovery of critical anatomical features challenging. This consequently leads to poor estimation of blood flow. In this work, we present a fluid-physics-constrained reconstruction framework that leverages topology optimization (TO) to jointly recover vascular geometry and blood flow directly from time-resolved CTA sinograms. The formulation couples a steady incompressible flow model with a transient advection-diffusion contrast transport model, mapped to sinogram space through a differentiable projection operator. The velocity field is recovered as part of the reconstruction, and thus hemodynamic information can be obtained without requiring a separate computational fluid dynamics pipeline. The proposed method is demonstrated on synthetic phantoms under varying sparsity and noise levels, and on representative projection data.

cs.CE

新论文 · v1arXiv:2611.09798

并行智能体团队:测试时计算扩展的更优方式

Test-Time Compute Scales Better with Parallel Agent Teams

Junlin Wang, Haozhe Chen, Ang Li, Rahul Chalamala, Zhuang Liu

AI 速读 基于摘要

作者提出并行智能体团队方法,通过并行采样多个小型协作团队并保留最佳团队结果,在长程任务上更有效地扩展测试时计算。

cs.AI

查看原文摘要

Test-time scaling improves the performance of a fixed model by spending more computation at inference. There are two common ways to spend it on agents when a verifier can score every attempt. Best-of-N sampling runs many independent agents and keeps the best result but saturates quickly. One large team of collaborating agents can score higher but stops improving as it grows. Can we get the best of both? Our method, parallel agent teams, does so by sampling many small teams in parallel and keeping the best team's result. We test it on 12 long-horizon tasks from GPU kernels and formal proofs to exploit development. With a 27B model and a budget of 100 agents, parallel teams of ten beat parallel agents on 10 of 12 tasks and beat one team of 100 on all four tasks where we ran such large teams. At equal dollar cost the same parallel teams beat a frontier model on half the tasks. A simple statistical model shows that individual agents lose because their many samples have a low mean and that one large team loses because a single sample gets no gain from variance. Sampling many small teams in parallel balances a high mean with the gain from variance. Parallel agent teams thus offer a more effective way to scale test-time compute.

新论文 · v1arXiv:2611.09075

Large Language Model Deployment on Resource-Constrained Edge Devices: A Practitioners Survey

Rahul Maliakkal, Yashasvi Makin, Plawan Rath, Rohit Jain, Ankur Sadhoo

原文摘要

Large Language Models (LLMs) have transformed many areas of artificial intelligence (AI), but their substantial resource requirements limit their deployment on mobile and edge devices. Although LLMs have demonstrated impressive capabilities in various applications, the next challenge is deploying these models on resource-limited edge devices. Recent innovations in software optimizations and specialized hardware have made it feasible to deploy LLMs on edge devices. Edge deployment offers benefits including local data processing, cost savings, reduced latency, and personalized responses. This paper reviews the latest techniques that make the deployment of LLMs on edge devices feasible.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.07676

$O(1/n)$ Convergence Rate for RVI $Q$-Learning

Avik Kar, Siddharth Chandak, Rahul Singh, Shalabh Bhatnagar

原文摘要

We establish finite-time convergence guarantee for synchronous relative value iteration (RVI) $Q$-learning for finite weakly communicating Markov decision processes (MDPs). For stochastic Krasnosel'skiĭ--Mann iterations driven by a non-expansive, linearly regular map on a finite-dimensional normed space, we establish last-iterate mean-squared residual bounds under martingale-difference noise whose conditional second moment grows at most linearly with the squared residual. Suitable polynomial stepsizes of order $n^{-a}$ yield an $O(n^{-a})$ rate for $0<a\leq1$. We verify linear regularity and the noise condition for the centered Bellman operator for finite weakly communicating MDPs. Applying the general result gives an $O(n^{-1})$ bound on the mean-squared Bellman span residual of RVI $Q$-learning iterates when a suitable stepsize sequence is used. The positive gap between optimal and suboptimal stationary deterministic policies then yields an $O(n^{-1})$ bound on the expected suboptimality of the greedy policy. Consequently, $O(ε^{-1})$ synchronous iterations suffice for an $ε$-optimal policy in expectation. These guarantees are instance-dependent, with constants that depend on the hitting-time parameters and the suboptimality gap of the second-best policy.

cs.LG

新论文 · v1arXiv:2611.07474

Adversarial Robustness of Kernel Machines: A Comprehensive Analysis

Rahul Kumar Yadav, Tunir Ghosh, Sudhendu Ahir, Parthe Pandit, Arjun Bhagoji

原文摘要

Kernel machines are an important class of models in machine learning. However, the question of how robust modern kernel machines are to adversarial examples has not been studied comprehensively. In this paper, we provide a thorough empirical investigation of the adversarial robustness of kernel-based models for both binary and multiclass classification tasks, via white-box and black-box evasion attacks. We evaluate the native robustness of kernel machines, random feature classifiers, and the relatively newer Recursive Feature Machines. In addition, we provide an algorithm for approximate adversarial training of kernel machines. Our experiments on classification tasks on image and tabular datasets strongly indicate that kernel machines are natively more robust than neural networks, i.e., their performance degrades more gracefully against adversarial perturbations.

cs.LG · cs.AI

新论文 · v1arXiv:2611.05748

Energy-Efficient Reinforcement Learning for Large Language Models

Rahul Sharma, Nitin Vegesna, Yanxin Zhang

原文摘要

Reinforcement learning for language models alternates between generating responses and training the policy. These stages place different demands on GPUs, creating opportunities to reduce clock frequency with little loss in throughput. Selecting frequencies online is difficult because response lengths change and frequency trials themselves consume time and energy. We present EE-RL (energy-efficient RL), an online controller that selects separate frequencies for generation and training during RL execution. It compares candidate settings with a prediction of the default GPU governor on the same token workload, and keeps the most energy-efficient setting that meets a throughput threshold. The controller then monitors throughput and energy and adjusts frequencies as the workload changes. Fixed-frequency sweeps on H100 and GB200 show GPU energy savings of up to 28.2% per valid training token across synchronous and asynchronous execution, while largely preserving throughput. EE-RL turns this headroom into online savings, reducing GPU energy per valid training token by up to 16.9% at a modest throughput cost.

cs.DC

版本更新 · v3arXiv:2610.01421

Robust and leakage-resilient device-independent oblivious transfer in MiniQCrypt

Rishabh Batra, Zhili Chen, Rahul Jain, YaoNan Zhang

原文摘要

Assuming post-quantum one-way functions, we construct device-independent oblivious transfer and bit commitment that tolerate independent honest faults at a constant rate and adaptive, bidirectional quantum leakage between the laboratories at a constant rate. Honest parties use trusted classical computation to operate untrusted quantum devices, which may share arbitrary entanglement and perform joint measurements without assumptions of independence or identical distribution. Security is simulation-based against quantum polynomial-time adversaries and composes sequentially with efficient simulators. For security parameter $λ$ and a prescribed total leakage budget $\ell$, one complete one-bit oblivious transfer uses $Θ(\ell+\log^2λ)$ device coordinates in at most three single-use device windows, including preprocessing, and polynomial classical computation and communication. The leakage budget is shared across these windows. The commitment has efficient simulators against both parties and yields device-independent coin tossing with abort; each uses one window. Completeness of oblivious transfer gives device-independent secure computation with abort for every efficiently computable classical functionality on a fixed number of parties, against static corruption of any proper subset, provided each reached call to oblivious transfer satisfies the device and budget conditions. The construction combines short selectors with code-based choice masking, a global audit, and error correction across field symbols. The commitment extractor changes a classical code coset while leaving the device execution and its leakage unchanged. Sender security uses a global Fourier analysis and a selector-aware Magic Square repetition bound derived from the two-round threshold theorem of Kundu and Tan (2023).

quant-ph · cs.CR

版本更新 · v2arXiv:2611.02253

Calibration-Constrained Diagnostics for Evaluating LLM Self-Evaluation

Jae Oh Woo, Mengdie Flora Wang, Rahul Ghosh, Baishali Chaudhury, Mun Young Kim

原文摘要

We introduce a reusable evaluation artifact for diagnosing whether LLM self-reported confidence can support confidence-gated act-or-defer decisions. The artifact is designed for evaluation rather than safety certification: it provides a black-box protocol, prompts, judge-reference labels, model outputs, reproduction scripts, and calibration-constrained diagnostic metrics for auditing LLM self-evaluation across math, factual, and commonsense reasoning tasks. Our central finding is that aggregate uncertainty summaries can produce deployment-misleading rankings: a model that appears strongest under standard aggregate calibration metrics can fail under category-level calibration constraints, while a model with worse aggregate calibration can exhibit stronger calibration-constrained behavior in the positive-margin region where high self-selection accuracy and tight calibration coexist. To expose this failure mode, we define PVC and C-PVC as category-level diagnostics over an accuracy-by-calibration surface: PVC counts categories whose self-evaluation accuracy exceeds a threshold, while C-PVC additionally requires category-level calibration error below a tolerance. We aggregate these diagnostics using Volume Under Surface (VUS) and a positive-margin restriction; they are VC/fat-shattering motivated but are empirical evaluation proxies, not literal VC-dimension estimates. Across 13 models and four benchmarks, the artifact shows weak confidence-correctness separation, stable diagnostic rankings under alternative categorizations and judge-label perturbations, and persistent positive-margin failures not captured by ECE or Brier score. Confidence-gated self-evaluation therefore requires calibration-constrained, category-level diagnostics, and we provide a reusable artifact for applying them under black-box access.

cs.AI