跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

跟进版本变化

查看已发布论文的最新修订，在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1318新增论文
+981其中 AI 相关
+159已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-13 11:13 · 全站最近入库：2026-11-13 14:16各信源进度 →

统计口径与数据新鲜度

统计 2026-11-12 14:16 — 2026-11-13 14:16（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：2026-11-13 11:13最近发现新增版本：2026-11-13 14:16库内论文最新更新时间：2026-11-13 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。

22,993 已收录论文19,304 AI 相关6,540 有修订112 HF 社区发现

论文修订列表

研究日报 / 周报 →按信源浏览 →

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 6,540 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-13 11:11（北京时间）
版本更新 · v2arXiv:2510.16785

Robust Reasoning Segmentation for Open-World MLLMs without Catastrophic Forgetting

Jiazhen Liu, Long Chen

原文摘要

Ensuring trustworthiness and versatility in Open-World Visual Recognition is a core goal of Multimodal Large Language Models (MLLMs). While integrating segmentation is desirable, prevailing methods require invasive fine-tuning, which often leads to catastrophic forgetting of the model's general-purpose capabilities. This trade-off between task-specific performance and general reliability fundamentally undermines the goal of building unified, trustworthy systems. We introduce LENS (Leveraging kEypoiNts for MLLMs' Segmentation), a novel plug-and-play paradigm designed to equip MLLMs with pixel-level ability without compromising their foundational integrity. LENS attaches a lightweight head to a completely frozen MLLM, interpreting the intrinsic spatial cues embedded in attention maps. It extracts keypoints and translates them into prompt-compatible features for a mask decoder. Extensive experiments validate that LENS achieves segmentation performance competitive with retraining-based methods. Crucially, it largely preserves the MLLM's open-world generalization, avoiding the degradation observed in fine-tuned counterparts. By decoupling segmentation from generation, LENS offers a robust and efficient path toward truly multi-talented and reliable vision models.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.14203

Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation

NVIDIA, :, Jiahui Huang, Jiawei Ren, Michal Tyszkiewicz, Bjoern Haefner, Michael Shelley, Xin Kang 等 17 位作者

原文摘要

3D simulation platforms are critical for autonomous driving because they enable end-to-end policy evaluation, thereby reducing development costs and improving safety. In recent years, neural simulation has become predominant, with methods such as NuRec playing a central role; however, these methods remain relatively slow and typically require per-scene tuning. In this work, we present Instant NuRec, a feed-forward neural reconstruction model that turns a short multi-view driving log into a fully simulatable 3D Gaussian Splatting (3DGS) world in a single forward pass. The model accepts multi-view input from a calibrated camera rig and emits a layered output consisting of static and dynamic 3DGS layers, a sky cubemap, and per-camera ISP corrections, while providing native support for non-pinhole camera models via 3DGUT. It reconstructs a 10-20-second multi-camera scene in roughly 1.5 seconds and achieves a PSNR on the Waymo Open Dataset that is 2.01 dB above the strongest evaluated baseline. Instant NuRec is deeply integrated into NuRec and is compatible with AlpaSim for closed-loop simulation.

cs.GR · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.22204

FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation

S M Ruhul Kabir Howlader, Xiao Chen, Yifei Xie, Lu Liu

原文摘要

Federated learning (FL) encounters substantial challenges due to heterogeneity, leading to gradient noise, client drift, and partial client participation errors, the last of which is the most pervasive but remains insufficiently addressed in current literature. In this paper, we propose FedAdaVR, a novel FL algorithm aimed at solving heterogeneity issues caused by partial client participation by incorporating an adaptive optimiser with a variance reduction technique. This method takes advantage of the most recent stored updates from clients, even when they are absent from the current training round, thereby emulating their presence. Furthermore, we propose FedAdaVR-Quant, a server-side memory compression variant that stores historical client updates in quantised form (while keeping client-server communication in full precision), reducing the server memory footprint of FedAdaVR by 50% (FP16), 75% (Int8), and 87.5% (Int4) while maintaining highly competitive, and occasionally superior model performance. We analyse the non-convex convergence behaviour of FedAdaVR with Adagrad and prove that our proposed framework eliminates the first-order partial client participation bias while improving monotonically with cohort size. Extensive experiments conducted on multiple vision and NLP datasets demonstrate that FedAdaVR consistently outperforms state-of-the-art baseline methods.

cs.LG · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.30907

Near-Quadratic Time Multivariate Polynomial Interpolation

Chandra Kanta Mohapatra

原文摘要

Let $\F$ be a finite field. Given $N$ distinct points $\bmα_1,\ldots,\bmα_N \in \F^m$ and associated values $β_1,\ldots,β_N \in \F$, we study the problem of computing an $m$-variate polynomial $f(\vy) \in \F[\vy]$ of individual degree less than $d$, with $d^m \ge N$, that satisfies $f(\bmα_i)=β_i$ for all $i\in[N]$, whenever such an $f$ exists. This is known as the\textit{ multivariate polynomial interpolation} problem. In this work, given $N=d^m$, we present a deterministic algorithm for multivariate polynomial interpolation over an arbitrary finite field $\F$ that runs in near-quadratic time $N^{2+o(1)}\poly(m,d,\log|\F|)$, assuming $d$ is $ω(1)$. This bound holds whenever the associated \emph{multivariate Vandermonde} matrix is nonsingular, has constant co-rank, or admits some special structure. In the general case, we give a randomized Las Vegas algorithm attaining the same near-quadratic running time, provided the finite field is sufficiently large and $d$ grows similar to the previous case. Unlike other multivariate interpolation strategies, we do not assume black-box access to the polynomial. In particular, we are not permitted to query arbitrary input points to obtain their evaluations. Our interpolation result follows by combining Wiedemann's classical approach~\cite{w86} for solving sparse linear systems with known bounds for fast \emph{multivariate multipoint evaluation} over finite fields~\cite{umans08, KU11, BGKM23, BGGKU24}. Specifically, our deterministic interpolation strategy relies on a deterministic variant of Wiedemann's approach, which is more commonly used in the randomized setting.

cs.DS · cs.CC · cs.SC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.01509

A linear edge bound for k-quasi-planar graphs

Ankan Sadhu

原文摘要

We prove the $k$-quasi-planar graph conjecture for topological drawings. For every integer $k\ge 2$, a simple graph on $n\ge 3$ vertices admitting a drawing with no $k$ pairwise crossing edges has at most $1056(k-1)^2(n-2)$ edges. Thus the number of edges is linear in $n$, with an explicit quadratic dependence on $k$. The result allows multiple crossings between the same pair of edges, including edges with a common endpoint. The proof uses the double of a sphere with boundary to represent graph edges by closed geodesics on a hyperbolic surface. The endpoints of geodesic lifts induce partial orders of width at most $k-1$. A stability bound for greedy chain partitions, together with a counting argument over a triangulation, gives the stated edge bound.

math.CO · cs.CG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.02985

Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores

Zeyu Zhang, Bradly C. Stadie

原文摘要

The standard check for contamination in LLM backtests is simple: compare scores before and after the training cutoff. We show this check is uninformative. Four flagship models fail it on questions they cannot have memorized: every scored question resolved after their cutoffs. The reason is structural. Models legitimately know more about times near their cutoff, so recency mimics leakage, and we prove no passive backtest can separate the two from genuine skill. Measurement, not just detection, requires information from outside the backtest. We supply it in two forms. A known cutoff identifies leakage at the boundary; a matched clean control identifies it globally and yields a leakage-adjusted score. Under a convex-pull model, leakage concentrates on outcomes that surprised the crowd and that training covered well. Partial memorization gives a large part of the full inflation. In twin models with planted leakage, the estimators detect and localize it, track its dose, and return null on clean questions. On frontier models, the estimators detect one cutoff-localized signature. They find no significant leakage at the tested boundaries in five models with positive naive gaps. Backtests need not be discarded; they need one defensible reference.

cs.LG · cs.CL · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.20627

When Failures Propagate: Causal Failure Attribution in Agentic Retrieval-Augmented Generation

Lauren Pothuru, Spurthi Setty, Natan Vidra

原文摘要

Agentic retrieval-augmented generation (RAG) interleaves retrieval, reasoning, and answer generation across multiple hops. A retrieval error at hop 1 can surface only as a wrong answer at hop 3, while later retrieval can also repair the trajectory. This paper introduces AgenticRAG-FP, an interventional benchmark for causal failure attribution in agentic RAG. The benchmark injects a certified fault at a specified hop, re-executes the downstream trajectory, and evaluates diagnosers against the known intervention site. Its central question is whether a post-hoc trace still identifies the injected hop after the suffix changes. In the dense Claude Haiku 4.5 structural sweep on three-hop MuSiQue questions, coverage-based diagnosis is 0.91 at hop 1 and 0.00 at hops 2 and 3 (n=43,36,21 failed trajectories), but it predicts hop 1 in 96% of failures, an earliest-hop rule; at hops 2 and 3, an LLM judge and frozen-hop repair localize only 0.25 to 0.48 of failures. In larger content-corruption runs, depth-2 exact-hop accuracy is 0.00 for coverage, 0.49 for an LLM judge, 0.59 for frozen-hop repair, and 0.14 for suffix regeneration (n=51); the judge and frozen-hop repair do not significantly differ (exact McNemar p=0.33).

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.26963

MARS: Towards High Goodput and Low KV Thrashing in Agent Serving under GPU Memory Constraints

Yifei Wang, Tsun-yu Yang, Hancheng Ye, Yechen Xu, Cong Guo, Chiyue Wei, Qinsi Wang, Dongting Li 等 12 位作者

原文摘要

Self-hosted LLM agents offer greater control over sensitive data and model customization while avoiding per-request API fees. However, serving concurrent, multi-turn workflows within limited GPU memory makes it difficult to achieve high workflow-level goodput. In particular, as workflows accumulate context, their reusable key-value (KV) caches can easily outgrow GPU capacity, triggering repeated eviction and recovery, known as KV cache thrashing. This process consumes resources and delays workflow completion. Although existing approaches propose various methods, our motivation study shows that the evaluated baselines still incur substantial thrashing overhead or fail to address the workflow-level goodput issue. We present MARS, an agent serving system that coordinates workflow admission and in-engine scheduling to achieve high workflow-level goodput on memory-constrained devices while avoiding KV cache thrashing. Specifically, outside the engine, an admission controller selects root workflows using initial prefix footprint estimates and live KV availability, adapting admissions to memory pressure. Inside, an agent-centric scheduler prioritizes turn completion and coordinates prefill allocation with KV reclamation to reduce disruptive evictions. Across two models and three GPU configurations, MARS achieves 1.59x-7.56x mean end-to-end latency speedups over the fastest baseline. Integrated as the serving backend for OpenCode, Codex, and OpenHands, MARS further improves mean workflow completion time by 1.17x-1.87x. Our source code is publicly available at https://github.com/Afterglow231/MARS_preview .

cs.OS · cs.DC · cs.LG · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.01411

Mean field optimal Core Allocation across Malleable jobs

Zhouzi Li, Mor Harchol-Balter, Benjamin Berg

原文摘要

Modern data centers and cloud computing clusters are increasingly running workloads composed of malleable jobs. A malleable job can be parallelized across any number of cores, yet the job typically exhibits diminishing marginal returns for each additional core on which it runs. Examples of malleable jobs include machine learning tasks, parallelized across multiple GPUs, and large-scale database queries, parallelized across multiple servers. Given the prevalence of malleable jobs, theoretical works have posed the problem of how to allocate a fixed number of cores across a stream of arriving malleable jobs so as to minimize the mean response time across jobs. We refer to this as the Core Allocation to Malleable jobs (CAM) problem. Although quite a few recent papers have been written on CAM, the problem remains challenging to solve optimally. In particular, prior theoretical work has only solved the CAM problem in very constrained cases. This paper takes a new approach to CAM, looking at the problem in the mean field asymptotic regime. In this regime, we are able to optimally solve a much more general instance of CAM. We derive two distinct mean field optimal policies, FW-CAM and GLAM. FW-CAM demonstrates a new intuition: in the mean field regime, individual job sizes are not relevant in finding an optimal policy. GLAM (Gittins-Like Allocation for Malleable jobs) is asymptotically optimal under certain common assumptions, and also serves as a good heuristic outside of the asymptotic regime by adapting dynamically to the current number of jobs in the system. Notably, none of the policies previously proposed in the literature are mean field optimal when jobs follow different speedup functions.

cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2602.23811

Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies

Xiang Li, Yuheng Zhang, Nan Jiang

原文摘要

We investigate the theoretical aspects of offline reinforcement learning (RL) under general function approximation. While prior works (e.g., Xie et al., 2021) have established the theoretical foundations of learning a good policy from offline data via pessimism, existing algorithms that are computationally tractable (often in an oracle-efficient sense), such as PSPI, only apply to finite and small action spaces. Moreover, these algorithms rely on state-wise mirror descent and require actors to be implicitly induced from the critic functions, failing to accommodate standalone policy parameterization which is ubiquitous in practice. In this work, we address these limitations and extend the theoretical guarantees to parameterized policy classes over large or continuous action spaces. When extending mirror descent to parameterized policies, we identify contextual coupling as the core difficulty, and show how connecting mirror descent to natural policy gradient leads to novel analyses, guarantees, and algorithmic insights, including a surprising unification between offline RL and imitation learning.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.01404

BOA Constrictor: Squeezing Performance out of GPUs in the Cloud via Budget-Optimal Allocation

Zhouzi Li, Cindy Zhu, Arpan Mukhopadhyay, Mor Harchol-Balter, Benjamin Berg

原文摘要

The past decade has seen a dramatic increase in demand for GPUs to train Machine Learning (ML) models. Because it is prohibitively expensive for most organizations to build and maintain a large GPU cluster, organizations instead choose to rent GPUs from cloud providers. The customer is responsible for devising a policy for (i) deciding how many GPUs to rent at every moment in time to process a stream of ML training jobs and (ii) allocating the rented GPUs among the currently active jobs in the system. Because ML training jobs can be parallelized across different numbers of GPUs, the customer generally has many options for how many GPUs to use for each job. Allocating more GPUs to a single training job will cause the job to complete more quickly. However, the customer pays for each GPU-hour they use, and a training job receives a diminishing marginal benefit from running on additional GPUs. Hence, allocating too many GPUs to a single training job can dramatically increase the overall cost that the customer pays to the cloud provider. This gives rise to a cost-performance tradeoff that customers must balance when running training jobs in the cloud. To balance the cost-performance tradeoff, we develop BOA Constrictor, a new scheduler for ML training jobs which uses a Budget-Optimal Allocation (BOA) policy to squeeze the highest level of performance out of a cloud-deployed GPU cluster given a fixed budget constraint. We explicitly formulate the problem as a budget-constrained scheduling problem and derive the BOA policy which minimizes the average job completion time (JCT) of a stream of arriving jobs subject to the user's budget. For a given budget level, we demonstrate that BOA Constrictor can reduce average JCT by 1.6 times in small-scale implementation experiments and by 2 times in detailed, large-scale simulations compared to state-of-the-art heuristic based schedulers.

cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2407.01176

Platform Building with Fake Users: On Airdrop Farmers and Activity Procurement

Hanna Hałaburda, Benjamin Livshits, Aviv Yaish

原文摘要

Digital platforms reward observable claims to build their user base. Because claims are imperfect proxies for people, these programs attract bonus hunters and airdrop farmers, who are usually treated as leakage and screened out. We show that screening can be too aggressive when eligibility requires a separable platform-building input. In a monopolist model, fixed per-claim rewards cannot implement finite farmer activity: rewards below farmer cost induce no entry, while rewards above cost induce unbounded entry. A shared pool can succeed because it makes claims rivalrous. Entry dilutes the pool until the per-claim reward equals claim cost, converting the program into identity-blind procurement. In the baseline model, all farmer-created claims have the same lower cost, while all organic claims have the same higher cost; farmers therefore supply the activity. Organic users receive no rewards but benefit from higher quality, so perfect screening can reduce platform profit and organic-user payoffs. In case when primary organic claims are cheaper but additional organic identities cost more than farmer claims, a small pool attracts only organic claims, whereas a larger pool recruits farmers to expand activity. The mechanism applies to separable inputs (e.g., liquidity, inventory, and data) rather than rewards for regular use or mechanical claim creation. Thus, weak identity changes both leakage and how platforms procure growth.

cs.GT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.10648

PENSA: A Spatial Accelerator for BitNet b1.58 Inference on an HBM-equipped AMD Alveo FPGA

Karthikeyan B. Kalyanasundaram, Ivan S. Maksymov, Philip H. W. Leong

原文摘要

Ternary large language models (tLLMs) replace general multiplication in dominant linear layers with sign-controlled accumulation, shifting hardware bottlenecks toward packed-weight delivery, reduction, and operator occupancy. PENSA is an end-to-end FPGA accelerator for the BitNet b1.58 2B4T model on an AMD Alveo U50. Two row-partitioned ternary matrix engines consume packed TQ1_0 weights from eight independent high-bandwidth memory (HBM) pseudo-channels, each processing 1,280 ternary weights per cycle through sign selection and integer reduction. The sequencer, attention, and vocabulary-projection units remain resident on the FPGA, while two-stream interleaved scheduling overlaps sequences across the persistent pipeline to form the Penta-Unit. At 104.1~MHz, PENSA achieves 58.09 tok/s at context 128 and 24.60 tok/s at context 2048, corresponding to 2.14-3.14$\times$ the throughput of a same-model Xeon E-2356G baseline. The resulting system demonstrates end-to-end FPGA execution of 2B-scale BitNet topology without modifying its model structure.

cs.AR · eess.SP

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2404.09443

Hybrid FedGraph: An efficient hybrid federated learning algorithm using graph convolutional neural network

Jaeyeon Jang, Diego Klabjan, Veena Mendiratta, Fanfei Meng

原文摘要

Federated learning is an emerging paradigm for decentralized training of machine learning models on distributed clients, without revealing the data to the central server. Most existing works have focused on horizontal or vertical data distributions, where each client possesses different samples with shared features, or each client fully shares only sample indices, respectively. However, the hybrid scheme is much less studied, even though it is much more common in the real world. Therefore, in this paper, we propose a generalized algorithm, FedGraph, that introduces a graph convolutional neural network to capture feature-sharing information while learning features from a subset of clients. We also develop a simple but effective clustering algorithm that aggregates features produced by the deep neural networks of each client while preserving data privacy.

cs.LG · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.21334

Do Pathology Foundation Models Encode Disease Progression? A Pseudotime Analysis of Visual Representations

Pritika Vig, Ren-Chin Wu, William Lotter

原文摘要

Vision foundation models trained on discretely sampled images achieve strong performance on classification benchmarks, yet whether their representations encode the continuous processes underlying their training data remains unclear. This question is especially pertinent in computational pathology, where we posit that models whose latent representations implicitly capture ordinal disease progression may better reflect underlying biology, support more robust generalization, and enable quantitative analyses of features associated with disease transitions. Using diffusion pseudotime, a method developed to infer developmental trajectories from single-cell transcriptomics, we probe whether foundation models organize disease states along coherent progression directions in representation space. Across four cancer progressions and six models, we find that all pathology-specific models recover trajectory orderings significantly exceeding null baselines, with pathology vision-only models achieving the highest average fidelities. Model rankings by trajectory fidelity on reference diseases predict few-shot classification performance on held-out diseases ($ρ= 0.91$), and exploratory analysis shows cell-type composition varies along inferred trajectories in patterns consistent with known stromal remodeling. Together, these results suggest that vision foundation models can implicitly learn to represent continuous processes from independent static observations, and that trajectory fidelity provides a complementary measure of representation quality beyond downstream performance. While demonstrated in pathology, this framework could be applied to other domains where continuous processes are observed through static snapshots.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.31821

What the Query Remembers: Query Abstraction Governs Lexical and Dense Retrieval of Classical Arabic Poetry

Omar Farouk Zouak, Selma Mani, Larbi Said Chikh, Raid Abderrezak Ouahioune

原文摘要

How well a poetry archive can be searched depends on what the user still remembers, not only on what the model understands. We show this for Classical Arabic poetry, benchmarking nine dense encoders and BM25 over two corpora, three indexing modes and two evaluation protocols. Which retriever wins is governed by how much of a poem's wording the query still carries. On tip-of-the-tongue queries BM25 leads every dense encoder, including a large multilingual embedding model (Qwen3-Embedding-8B, 0.746 vs. 0.717 Recall@5); on abstract queries it falls to eighth out of ten (0.392 vs. 0.748). Editing the wording of the same queries shows that this ranking largely reflects query composition: adding one remembered half-verse raises BM25 by 38 points, rewriting the quoted words by hand leaves BM25 level with the 8B encoder, and BM25's sensitivity to remembered wording is significantly steeper than that of the strongest dense encoder. The same axis controls explanation augmentation, whose effect swings from +37 to -39 points. The mechanism splits by system type: lexical containment best predicts how BM25 responds to explanations, embedding proximity how dense encoders do. Finally, the field's two standard protocols, known-item retrieval and thematic relevance, dissociate on the same systems, a result reproduced by two blind human annotators and by two open-weights judges, one of them under a rubric with no literal-match criterion. A benchmark that reports one protocol, or one query register, can give a materially wrong picture. Code and data are available at https://github.com/Ellzo/what-the-query-remembers.

cs.CL · cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.31547

The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling

Andre Herz, Matthijs Pals, Daniel Durstewitz, Georgia Koppe

原文摘要

Dynamical systems reconstruction (DSR) aims to learn surrogate models that capture the dynamics underlying time-series data. Reliable scientific inference with these surrogates requires uncertainty estimates consistent with the learned dynamics. We expose a dynamic-probabilistic consistency (DPC) gap: optimizing finite-horizon probabilistic objectives can degrade the learned dynamics or decouple predictive uncertainty from the local tangent dynamics it should reflect. We isolate three mechanisms behind this gap: core collapse, noise masking, and blind uncertainty. Specifically, we show that open-loop rollout objectives can penalize covariance growth driven by the dynamics, encouraging optimization shortcuts that weaken local expansion. To mitigate this gap, we propose KAFFEE (Kalman-Aware Framework For Ergodic Emulation), a differentiable extended Kalman filter-based training framework that jointly learns dynamics and noise covariances by coupling filtered innovation likelihoods with covariance propagation through learned local Jacobians, while differentiating through the Kalman updates. On stochastic hyperchaotic Lorenz-96, KAFFEE mitigates the identified failure modes and improves both reconstruction of dynamical invariants and predictive scores relative to open-loop objectives. The DPC gap also appears when probabilistically adapting a DSR foundation model across 13 chaotic systems, where KAFFEE improves predictive likelihood over open-loop adaptation while preserving the pretrained model's long-term dynamics and enabling in-context Bayesian filtering.

cs.LG · math.DS · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.11872

LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection

Lanxin Zhao, Bamdev Mishra, Pratik Jawanpuria, Lequan Lin, Dai Shi, Junbin Gao, Andi Han

原文摘要

Orthogonal parameter-efficient fine-tuning (PEFT) adapts pretrained weights through structure-preserving multiplicative transformations, but existing methods often conflate two distinct design choices: the subspace in which adaptation occurs and the transformation applied within that subspace. This paper introduces LOFT, a low-rank orthogonal fine-tuning framework that explicitly separates these two components. By viewing orthogonal adaptation as a multiplicative subspace rotation, LOFT provides a unified formulation that recovers the multiplicative core of representative orthogonal PEFT methods, including coordinate-, butterfly-, Householder- (with a learnable support) and principal-subspace-based variants (up to scaling and relaxation). More importantly, this perspective exposes support selection as a central design axis rather than a byproduct of a particular parameterization. We develop a first-order analysis showing that useful adaptation supports should be informed by the downstream training signal, motivating practical task-aware support selection strategies. Across language understanding, visual transfer, mathematical reasoning, and multilingual out-of-distribution adaptation, LOFT with task-aware supports improves performance at matched trainable-parameter and transform settings under a shared protocol. This suggests that, under a fixed transform and budget, the choice of support affects performance, making systematic support selection an important direction for improving orthogonal PEFT.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.17757

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization

Zhongzhu Zhou, Donglin Zhuang, Jisen Li, Ziyan Chen, Shuaiwen Leon Song, Ben Athiwaratkun, Xiaoxia Wu

原文摘要

INT2 KV-cache quantization is attractive for long-context LLM serving, yet making it both accurate and practical remains challenging. Data-oblivious rotations such as Hadamard transforms flatten channel outliers, but still degrade sharply at INT2 because they ignore how downstream attention queries the cache. We propose OSCAR, an ultra-low-bit KV-cache quantization method that estimates attention-aware covariance targets offline and uses them to derive fixed per-layer rotations and clipping thresholds. By aligning the quantization basis with the second-moment structures consumed by attention, OSCAR preserves attention fidelity at 2-bit precision. Beyond theoretical analysis under a frozen-error surrogate, we build a serving-ready OSCAR system with fused Triton write and decode kernels that preserve paged KV-cache layouts and prefix caching, integrating into modern serving engines such as SGLang and vLLM. We evaluate OSCAR on reasoning and coding benchmarks with generation traces of up to 32K tokens across five tasks. On Qwen3-4B-Thinking-2507 and Qwen3-8B, OSCAR narrows the BF16 accuracy gap to 3.78 and 1.21 points, respectively, where Hadamard-only INT2 collapses, and matches BF16 within run-to-run variance on Qwen3-32B and GLM-4.7 (358B parameters). On RULER-NIAH up to 128K tokens, OSCAR substantially outperforms QuaRot-style INT2 across context lengths. System-wise, OSCAR compresses KV-cache memory by nearly $8\times$, boosts multi-request throughput by up to $7.8\times$ at large batch sizes within the same memory budget, and accelerates batch-size-1 decoding by up to $3.1\times$ over BF16 by cutting KV memory traffic.

cs.LG · cs.AI · cs.DC · cs.PF

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.29873

HAWK: Heterogeneity-Aware KV Cache Transfer for Efficient GPU-NPU Phase-Disaggregated LLM Inference

Junhyeok Park, Jungeun Yoon, Kyungmin Kim, Hunsoon Lee, Shinyoung Ahn, Kangho Kim

原文摘要

Large language model (LLM) inference exhibits distinct computational characteristics across its two phases: prefill is compute-intensive, whereas decode is more memory-bound. As a result, AI accelerators achieve varying levels of efficiency across the two phases. GPUs are well suited to prefill, but are often underutilized during decode. By contrast, NPUs can utilize their compute resources more effectively during decode. Motivated by this observation, we explore a heterogeneous architecture that integrates GPUs and NPUs, mapping prefill to GPUs and decode to NPUs to achieve high performance and efficiency. However, realizing such heterogeneous integration is challenging because LLM phase disaggregation requires KV cache transfer from prefill to decode (that is, from GPUs to NPUs), which is complicated by differences in inter-device communication mechanisms and KV cache tensor layouts. To address this, we propose HAWK, a transfer mechanism that enables rapid KV cache transfer across heterogeneous devices. HAWK establishes a remote direct memory access (RDMA) path for direct cross-device transfers while handling inter-device tensor layout discrepancies as part of the transfer process. In particular, HAWK allocates tensor-layout-aware RDMA buffers on the NPU side to match the target tensor layout. Leveraging these buffers, HAWK orchestrates data transfer from a conventional contiguous GPU RDMA buffer to the corresponding NPU buffers, allowing transferred tensors to be consumed directly without additional data rearrangement while maintaining transfer efficiency. We implement and evaluate HAWK on a system built with commercially available GPUs and NPUs, demonstrating performance within 7.88% of a GPU-only system under the same SLO constraints while achieving up to 1.26$\times$ higher power efficiency and 1.72$\times$ higher cost efficiency.

cs.AR · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.11714

Steering Emergent Behavior in Multi-Agent LLM Systems via Information Networks

Sepehr Ilami, Babak Heydari

原文摘要

Large language model (LLM) agents increasingly operate in groups, each pursuing an individual objective while jointly determining system performance. If an operator controls which agent observes which other agent, but not their payoffs or messages, how should observations be structured to raise collective welfare? We make the information network (who observes whom) a design object, decoupled from the fixed interaction network over which agents act. Ten identical LLM agents play repeated group-decision games; by default each observes only an anonymous summary of the group's previous-round outcome, and a manager with a fixed budget adds directed observation links that reveal peers' past actions. Across 1,080 episodes and six games spanning coordination, anti-coordination, social dilemmas, and discovery, we ask how much information to share and, at a fixed budget, who should observe whom. Disclosure creates behavioral coupling: observation acts as a contagion channel whose welfare effect depends on the alignment between individually attractive behavior and the collective objective. First, the value of information is alignment-contingent: more peer information tends to help or be neutral when individual behavior is aligned with the collective goal, but under free-riding or congestion externalities it amplifies collectively harmful behavior; in a public-goods game the group does best with no information at all. We read this sign separation as a cross-game regularity within one controlled LLM population, not a model-invariant law. Second, at a fixed budget, who observes whom matters primarily when coupling is harmful: a modular "barbell" that lets sub-populations entrench harmful behavior is reliably the worst wiring, reversing the network-reciprocity intuition from human evolutionary game theory. These results argue against a default of full transparency for agent collectives.

cs.MA · cs.AI · cs.GT · cs.SI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.18532

AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework

Inderjeet Singh, Haitham Mahmoud, Andrés Murillo

原文摘要

AI sandboxes produce evidence about systems that may act through software tools, networked devices, or physical actuators. The interpretation of that evidence depends on the boundary of the experiment. We define a sandbox apparatus, distinguish five overlapping archetypes, and specify fifteen claim-relative measurement dimensions. A weakest-link licensing rule caps a deployment claim at its weakest necessary evidence dimension. We connect this rule to a threat model covering both outward harm and corruption of the evaluation apparatus, then apply it to four worked examples spanning driving, industrial control, tool-using agents, and vision-language-action manipulation. We also map the required artifacts to standards and regulatory instruments. The framework identifies which claims a bounded experiment supports, which failures its controls contain, and which assumptions require further validation before deployment.

cs.CR · cs.AI · cs.RO · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.13292

Recovering Irreducible Three-Body Interactions with Lagrangian Neural Networks

Sena Kalabalik, Sukru Caglar, Abdullah Umut Hamzaogullari, Arkadas Ozakin

原文摘要

Lagrangian Neural Networks (LNNs) learn mechanical systems from trajectory data by parameterizing a scalar Lagrangian and deriving the dynamics through the Euler-Lagrange equations, biasing the model toward motion that respects the variational structure of mechanics. The interactions studied so far have been pairwise-additive, leaving open whether LNNs can recover an irreducible many-body interaction from motion alone. We address this using the Axilrod-Teller triple-dipole interaction, the leading three-body dispersion term, whose dependence on the collective geometry of three particles cannot be represented by any sum of pairwise terms. We prescribe the kinetic energy exactly and learn only the potential, as a function of interparticle distances and angles. Combined with a signal-aware sampling strategy that concentrates training data where the three-body signal is strongest while preserving broad coverage of configuration space, this recovers the interaction from accelerations alone. The learned potential reproduces the radial scaling, angular dependence, and characteristic sign reversal of the Axilrod-Teller interaction, and generates stable trajectories. Embedding it within a pairwise Lennard-Jones potential lets us examine its observability: the three-body term is recovered once its dynamical signature exceeds the residual modeling error, which it does cleanly at amplified coupling but not at the coupling of a real noble gas, bracketing the transition between the two. Finally, symbolic regression on the trained potential, with no assumed functional form, returns the Axilrod-Teller expression with angular numerator, radial law, and coupling constant intact. An LNN with domain-specific structure can thus recover an irreducible three-body interaction from trajectories as a closed-form law, pointing toward learning interaction laws whose structure is not known a priori.

cs.LG · physics.atom-ph · physics.comp-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.24954

JAREX: An Acquisition Function for Multi-Objective Algorithmic Process Characterization

Xinyang Li, Kevin Stone, Ajit Vikram

原文摘要

Pharmaceutical process characterization is central to Quality by Design because it defines how variations in process parameters affect the ability to meet product quality specifications, thereby supporting proven acceptable ranges and robust manufacturing. In practice, however, characterization still relies largely on factorial design of experiments (DOE) approaches, which are inefficient for resolving multivariate pass/fail boundaries in higher-dimensional spaces. While Bayesian optimization has transformed process optimization, adaptive methods for multi-objective process characterization remain lacking. Here, we introduce JAREX (Joint Acceptable Region EXploration), a Bayesian active-learning acquisition function for multi-objective process characterization. JAREX formulates characterization as a joint boundary-learning problem and adaptively selects experiments to recover the joint pass region defined by simultaneous satisfaction of threshold criteria across multiple objectives. JAREX combines an optimistic joint-feasibility mask with a multi-objective extension of randomized straddle, focusing sampling on the joint edge of failure. Our benchmark study suggests that JAREX provides more accurate and sample-efficient recovery of the joint pass region than factorial DOE, space-filling designs, and greedy objective-wise strategies over the full experimental budget range. For batched experimentation, it reduces the number of iterative process characterization experiments by more than half while preserving high accuracy for the boundary-identification task. Implemented in the open-source obsidian package, JAREX provides a modular framework for adaptive, data-efficient multi-objective algorithmic process characterization, supporting sample-efficient range finding in high-dimensional spaces.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.09119

Which Buildings Are Artificial Intelligence-Ready? A Measurement-Based Assessment Framework for AI Question Answering and Actuation

Wooyoung Jung

原文摘要

Agentic artificial intelligence (AI) systems are becoming the interface to buildings, answering questions and controlling operations, but a building's readiness for them has not been systematically assessed. This study proposes a framework to quantify it. First, a building's knowledge graph sets two ceilings. The answerable-readiness ceiling is the share of operational questions its data could answer, and the actuation-readiness ceiling is the share of control actions it exposes. Second, a reference AI agent's accuracy on a fixed set of these questions shows how much of the ceilings is realized. On a simulated office, the agent realizes 0.62 of a 0.64 answerable ceiling, so missing data, not the AI, limit readiness, except in naming a fault's cause. Across 37 public real-building graphs, the median answerable ceiling is 0.16, and in 15 of 45, unlinked sensors lower it. The framework turns "is this building AI-ready?" into an auditable, ranked retrofit question.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.10664

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions

Diancheng Kang, Zheyuan Liu, Ningshan Ma, Yue Huang, Zhaoxuan Tan, Meng Jiang

原文摘要

Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful dialogue. We identify KV-cache contamination as a key failure mode: steered token states are stored and repeatedly reused, turning a local perturbation into cumulative coherence degradation. To address this challenge, we propose Gated Cropped Attention-Delta steering (GCAD), which extracts steering signals from system-prompt contributions to self-attention and applies them with token-level gating. Across persona-steering experiments, GCAD preserves trait control while substantially improving long-horizon coherence. On the main multi-turn benchmark, GCAD improves average coherence drift from -18.6 to -1.9 and raises turn-10 trait expression from 78.0 to 93.1. These results suggest that activation steering becomes more reliable when interventions follow the prompt-mediated pathways that models already use for behavioral control.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2106.06801

Contrastive Semi-Supervised Segmentation with Class-wise Patches and Silhouette-Adaptive Consistency

Prashant Pandey

原文摘要

We present CSSL, a contrastive semi-supervised method for medical image segmentation. CSSL samples class-wise patches from labelled images and from confident pseudo-labels, separates their embeddings with a supervised contrastive loss with mixed hard negatives, and uses the Silhouette coefficient of the embedding clusters to set the strength of a feature-perturbation consistency loss. On MoNuSeg, patch embeddings are obtained by masked pooling of the encoder features of the unmasked image, nucleus rims form an additional contrastive class and a memory bank stores past embeddings; on CHAOS, patches are pixel-masked and no memory bank is used. The CSSL losses are added to a weak-to-strong pseudo-labelling recipe. We follow the protocols of published baselines: Self-Loop on MoNuSeg and DAFNet on CHAOS. On MoNuSeg with 50% labels, CSSL reaches 80.87 $\pm$ 0.17 nuclei F1 over three label splits, compared with 79.10 for Self-Loop and 78.73 for the same recipe without CSSL. On CHAOS T2 with 25% labels, CSSL reaches 89.01 Dice, compared with 82.0 for DAFNet and 88.94 for the recipe alone. Ablations show that the contrastive branch and, on MoNuSeg, the boundary class and feature-level pooling account for most of the improvement. Code: https://github.com/prinshul/CSSL

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.19806

The Art of Asking: Multilingual Prompt Optimization for Synthetic Data

David Mora, Viraat Aryabumi, Wei-Yin Ko, Sara Hooker, Julia Kreutzer, Marzieh Fadaee

原文摘要

Synthetic data has become a cornerstone for scaling LLMs, yet its benefits for multilingual modeling remain bottlenecked by translation. Translation for data augmentation inherits English-centric framing and style and neglects cultural dimensions, ultimately constraining model generalization. We argue that the overlooked prompt space offers a more powerful lever for improving multilingual performance. We introduce a lightweight framework for prompt-space optimization, where translated prompts are systematically transformed for Naturalness, Cultural Adaptation, and Difficulty Enhancement. Using an off-the-shelf multilingual LLM, we apply these transformations to prompts from 12 languages spanning 7 families. Under identical data conditions, our approach achieves substantial and consistent downstream improvements over the translation-only baseline: +4.7% accuracy on Global-MMLU, +2.4% XCometXL on Flores and +35.3% wins in preferences on mArenaHard. These gains are further corroborated by human preferences on open-ended creative writing. We establish prompt-space optimization as a simple yet powerful paradigm for building multilingual LLMs that are more robust, culturally grounded, and globally capable.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2508.20231

When Graph Structure Provably Helps Classification: Non-Asymptotic Recovery Guarantees

Firooz Shahriari-Mehr, Javad Aliakbari, Alexandre Graell i Amat, Ashkan Panahi

原文摘要

The joint use of graph structure and node-specific information is central to transductive node classification, yet a fundamental theoretical question remains: when does graph structure actually help? We provide the first deterministic, non-asymptotic, distribution-free answer to this question. We build on nuclear-norm graph clustering and generalized convex clustering. Our formulation of the latter incorporates node features, partial labels, and general convex loss functions, making it suitable for transductive node classification. We analyze each problem separately to characterize when graph structure alone, or node information alone, is sufficient for perfect recovery. We then formulate a unified convex optimization problem through a shared atomic norm representation and prove that combining the two sources expands the range of conditions under which perfect recovery is guaranteed beyond what either source alone can certify. This shows when node information can improve clustering and graph structure can improve classification.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2603.05066

Reward-Conditioned Reinforcement Learning

Michal Nauman, Marek Cygan, Pieter Abbeel

原文摘要

Sample-efficient reinforcement learning typically uses a fixed reward function both to guide exploration and to supervise learning. However, the same experience can provide supervision under multiple related reward specifications, even when the objective of interest remains fixed. We introduce Reward-Conditioned Reinforcement Learning (RCRL), an off-policy approach that collects experience under a nominal objective while training a reward-conditioned agent using counterfactual rewards recomputed from replay. RCRL constructs alternative reward specifications by perturbing the nominal reward, providing diverse supervision without additional environment interaction. Across single-task, multi-task, and vision-based control benchmarks, RCRL improves nominal task performance and sample efficiency when integrated with strong RL backbones. As a secondary capability, the learned policies support zero-shot behavioral adjustment toward related objectives without further training. These results demonstrate that diverse reward supervision can improve learning of a predefined objective while also enabling policy steerability.

cs.LG

查看论文
arXiv ↗PDF ↗