跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 16:31 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 18:17 — 2026-11-09 18:17（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 16:31最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

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 14,511 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 16:29（北京时间）
新论文 · v1arXiv:2611.09767

From PAC bounds on the generalization error to PAC bounds on the parameter estimation error

Mihaly Petreczky, John Leth, Emma Lukacs, Balint Daroczy

原文摘要

Probably Approximately Correct (PAC) bounds on the generalization error (the difference between the empirical prediction error computed on the training data and its expectation) are an established tool in statistical machine learning, and there have been several extensions of these bounds to dynamical systems. In parallel, in recent years, there has been growing interest in finite-sample bounds for parameter estimation error in system identification. The latter bounds tend to be algorithm-specific, relying on reformulating the identification algorithm as a least-squares regression problem. This is in contrast to classical PAC bounds, which are algorithm-agnostic and can be applied to any identification algorithm based on minimizing a cost function involving the empirical loss. In this paper, we show how oracle bounds derived from PAC bounds can be used to derive finite-sample bounds for dynamical systems. As an illustration of this approach, we present finite-sample parameter-estimation bounds for linear and bilinear systems with bounded inputs and noise. These bounds apply to identification algorithms based on minimizing a regularized empirical loss function. The key ingredient is to establish an oracle inequality, i.e., an inequality between the true prediction error of the learned model and the minimum achievable true prediction error, and then use either the convexity of the true loss or system-theoretic properties of the loss function to derive bounds on the parameter estimation error. We also analyze the rates of the obtained bounds and compare them with those of classical asymptotic results.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09763

Link-Level Performance Comparison of 5G Beamforming: Reciprocity-Based SVD vs. Codebook-Based Precoding

S. M. Haider Ali Shuvo, Seda Dogan-Tusha, Monisha Ghosh

原文摘要

Downlink (DL) precoding in mid-band MIMO relies on uplink (UL) sounding reference signals (SRS) with reciprocity-based singular value decomposition (SVD) or channel state information reference signals (CSI-RS) with codebook-based precoding matrix indicator (PMI) feedback. Although SVD precoding offers unquantized beamforming, it depends on a channel estimate from SRS transmitted at the limited user equipment (UE) power, whereas Type-I PMI is quantized but derived from a high-power CSI-RS based channel estimate. In this paper, we compare SRS-SVD and CSIRS-PMI for single-user MIMO through an end-to-end, 3GPP-compliant link-level simulation at 3.75 GHz with 100 MHz bandwidth, using a 192 antenna element gNB mapped into 32 ports, the 3GPP Release 19 UE antenna model, and ray-traced (RT) channels in Manhattan and Chicago. We show that neither scheme is uniformly superior: CSIRS-PMI serves weak and shadowed users better and reduces outage, whereas SRS-SVD achieves higher spectral efficiency (SE) and enables more multi-layer transmission for users with strong channels. The results on the Clustered Delay Line (CDL)-C statistical channel also confirm this crossover. We further show that by utilizing a simple logistic regression based on the received power of the standard CSI reference signal (CSI-RSRP) and the channel quality indicator (CQI), the gNB can select the optimal transmission scheme with around 90% accuracy, achieving an SE that closely approaches an ideal per-user selection.

cs.NI · eess.SP

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.15815

Privacy Filters are Captured by Residues: A Characterization of Free Natural Filters and the Cost of Adaptivity

Matthew Regehr, Bingshan Hu, Ethan Leeman, Pasin Manurangsi, Pierre Tholoniat, Mathias Lécuyer

原文摘要

We study privacy filters, which enable privacy accounting for differentially private (DP) mechanisms with adaptively chosen privacy characteristics. We show that the worst-case privacy loss of interacting with any privacy filter is characterized by a Bellman equation. We apply this theory to develop residue filters, which unify existing privacy filters. We develop the Gaussian DP (GDP) residue filter, which strictly improves upon the naïve GDP filter. We show that, in the average case, this new filter asymptotically permits as many pure DP queries as in the non-adaptive case and a factor $π/2$ more pure DP queries than the naïve GDP filter. We also show that residue filters capture the natural filter, which promises greater utility by leveraging exact privacy accounting techniques. Earlier privacy filters consider only simple privacy parameters such as Rényi-DP or GDP parameters. Natural filters account for the entire privacy profile of every query, promising more efficient use of a given privacy budget. We show that, contrary to other forms of DP, natural privacy filters are not free in general. We present a characterization of when a family of private queries admits free natural filters for a given budget. In particular, only families of privacy mechanisms that are totally-ordered when composed admit free natural privacy filters with respect to an arbitrary privacy budget. Finally, we show that, while the natural approximate-DP filter can fail in the presence of an adaptive adversary, it cannot fail too badly: the output remains approximate-DP with parameters at most poly-logarithmically worse than the intended privacy parameters.

cs.CR · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09759

A Tight Hierarchy for Chain of Thought

Thanh Le, A. Pavan, N. V. Vinodchandran

原文摘要

Chain-of-thought (CoT) reasoning has emerged as a powerful paradigm for extending the computational capabilities of transformer-based models. A growing body of recent work has begun to uncover the fine-grained computational power of transformers augmented with CoT, as well as their connections to classical complexity theory. In this work, we advance this line of research by establishing the first hierarchy theorem for CoT-based computation. Our main result shows that for any reasonable resource bound $r(n) \geq n$ and any $\varepsilon > 0$, \[ \mathrm{CoT}(r(n)) \subsetneq \mathrm{CoT}(r(n)^{1+\varepsilon}), \] where $\mathrm{CoT}(r(n))$ denotes the class of decision problems solvable by transformers using $O(r(n))$ CoT reasoning steps on inputs of length $n$. Our result shows that increasing the number of CoT reasoning steps provably yields strictly greater computational power, establishing CoT steps as a fundamental resource in transformer-based computation. Unlike classical hierarchy theorems, which are typically proved via diagonalization, our approach leverages known coarse-grained simulations between CoT-augmented transformers and Turing machines in both directions. Building on these connections, we adapt the classical padding technique from complexity theory to this setting to obtain a tight hierarchy. A key technical contribution of our work is the implementation of padding within the transformer-based CoT model.

cs.LG · cs.CC

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2505.23086

Equivariant Spherical Transformer for Efficient Molecular Modeling

Junyi An, Xinyu Lu, Yunfei Shi, Peijia Lin, Licheng Xu, Qianwei Tang, Chao Qu, Fenglei Cao 等 9 位作者

原文摘要

Equivariant Graph Neural Networks (GNNs) have significantly advanced the modeling of 3D molecular structure by leveraging group representations. However, message passing built only from exactly equivariant operations can have restricted practical expressiveness at a fixed representation degree. We introduce the Equivariant Spherical Transformer (EST), a plug-and-play module that applies Transformer attention to spherical spatial representations obtained from group representations. EST explicitly mixes information across sampled orientations, unlike prior orientation-wise spherical operations, while retaining a strong approximate equivariant inductive bias through near-uniform spherical sampling. As demonstrated by our experiments on challenging benchmarks like OC20, MPtrj and QM9, EST-based models achieve state-of-the-art performance. For the complex molecular systems within OC20, small models empowered by EST can outperform some larger models and those using additional data. We characterize the ideal closed-domain condition under which the continuous operation is exactly equivariant and empirically quantify the finite-sampling accuracy--equivariance--memory trade-off used in practice.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09747

Contention Resolution Against an Adversarial Scheduler

Michael A. Bender, Martín Farach-Colton, Andrew Krapivin, Pritom Kundu, John Kuszmaul, Margaret Kuszmaul, William Kuszmaul, Jingxun Liang

原文摘要

In the classical contention-resolution problem, a set of players share a broadcast channel, and a player succeeds in a given time step if it is the only player to broadcast during that step. Implicit in the classical problem is the assumption that every player is free to act on every step: once a player arrives, it participates until it succeeds. We study what happens when that assumption is removed. In our model, an adversarial \emph{scheduler} decides, on each step, which subset of the players gets scheduled to participate in the step. An unscheduled player simply sleeps through the step. We measure a protocol by its \emph{efficiency}: the number of players divided by the expected number of steps in which at least one player was active. Our first result says that, so long as the players are given access to a global clock and to shared randomness, they can achieve efficiency $Ω(1/\log n)$. The players are able to achieve this bound without requiring any channel feedback, and even if the adversarial scheduler is adaptive. We also give a matching lower bound of $O(1 / \log n)$, which holds even with channel feedback, and even for an oblivious scheduler. Our upper bounds all require the players to have access to a shared global clock and to shared randomness. Our final result says that this type of implicit shared state is necessary. If the players have neither a global clock nor shared randomness, then no protocol can achieve efficiency better than $O(\log n / n)$; and this holds even if the other aspects of the problem are designed to be as favorable for the players as possible (the channel gives ternary feedback and the adversary is oblivious).

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09740

Zero-Shot Benchmarking of Unified Multimodal Models for Shallow-Water UAV Image Distortion Assessment and Restoration

Dario Scilla, Omar A. Lopez, Mattia Rosso, Kasper Johansen, Matthew F. McCabe

原文摘要

Shallow-water UAV imagery provides centimeter-scale observations of benthic environments, but water-induced distortions complicate interpretation. To our knowledge, we present the first systematic zero-shot benchmark of unified multimodal large language models (MLLMs) for both assessing water-induced distortions and restoring shallow-water imagery within the same model framework. We evaluate five open-weight unified MLLMs with frozen pretrained weights and without access to paired reference images or descriptions of the true seabed. The benchmark contains 1,000 image pairs: 600 semi-synthetic UAV scenes created by applying synthetic water distortions to real shallow-water imagery and 400 fully synthetic through-water scenes. Three independent human annotations cover five distortion types. We evaluate four assessment prompts (P0-P3), from direct instruction to structured task decomposition, on all 1,000 images and four diagnosis-guided restoration prompts (R0-R3) on a common 100-image subset. Assessment varies substantially by model and prompt, with systematic prediction biases and a best pooled balanced accuracy of 0.654 for distortion presence. The best pooled PSNR gain is +0.255 dB, no unified MLLM improves pooled LPIPS, and some outputs alter scene structure or hallucinate content. Two restoration-only baselines also show limited transfer: InstructIR achieves a pooled PSNR gain of +0.040 dB, while PromptFix degrades all four pooled metrics under every prompt. These results show that recognizing shallow-water degradation does not imply reliable physical restoration and provide a reproducible baseline for future work.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09736

Safety Is $Π_1$, Provability Is $Σ_1$: One Framework for the Hugging Face Breach and OpenAI's Mathematical Proofs

Jinho Kang, Jinsook Kim

原文摘要

OpenAI's agents breached Hugging Face in July 2026, and the same company released more than seven hundred AI-generated manuscripts of mathematical proofs in October 2026. The first event is read as a failure in security, while the second is read as a success in mathematics. We read both through the hybrid framework of our paper (Kim and Kang, 2026, arXiv:2611.01914), in which coding, proving, and learning from data are derivations by one and the same deductive mechanism, distinguished by the kinds of premises from which they are derived. Under this framework, the AI systems behind the two events ran the same loop, in which a statistical proposer produces candidate exploits or proofs and a deductive verifier settles each one by a derivation. What separates the events is the logical form of the statement wanted by each of the two domains, security and mathematics. The safety of a program is a $Π_1$ statement, for it says that no exploit exists, which is not assured by any finite list of tests that have been passed by the program. By contrast, the provability of a sentence is a $Σ_1$ statement, for it says that a proof exists, which is assured by a single instance, namely a proof that has been checked by the deductive verifier. The theorem behind both is Turing's Undecidability Theorem: the halting set is $Σ_1$ but not decidable, so its complement is $Π_1$ and not $Σ_1$, which is to say that membership has a finite witness but non-membership has none. We prove that attaching a statistical proposer to a deductive verifier does not change this undecidability result, however good the proposer is. We then discuss what does assure safety and where the residual risk goes.

cs.LG · cs.AI · cs.CR · cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.11884

Sobolev Regularized MMD Gradient Flow

Chenyang Tian, Bharath K. Sriperumbudur, Arthur Gretton, Zonghao Chen

原文摘要

We analyze Sobolev descent, a regularized variant of maximum mean discrepancy (MMD) gradient flow based on a gradient penalty on the MMD witness function. This regularization mitigates the non-convexity of the MMD objective, and yields provable \emph{global} convergence guarantees in MMD, in both continuous and discrete time. A surprising appeal is that our convergence analysis does not rely on isoperimetric assumptions on the target distribution. Instead, it is based on a regularity condition on the difference between kernel mean embeddings. We extend Sobolev descent such that it is applicable in both sampling (from an unnormalized target distribution)---using Stein kernels---and generative modeling settings, unlike previous works, where a gradient flow is suitable for only generative modeling or sampling but not both. We empirically validate the method on a broad range of tasks across both settings.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09734

GuardrailAgent: An Agentic Framework for Jailbreak Defense

Tianze Chang, Junjie Chu, Yixin Wu, Michael Backes, Yang Zhang

原文摘要

Despite undergoing safety training to align with human values, large language models (LLMs) remain vulnerable to jailbreak attacks that circumvent built-in safeguards and elicit malicious behaviors given by the adversary. Existing defenses are mostly static and fail to adapt to new or unknown attack strategies, providing limited resilience. To address these, we propose a multi-agent defense framework, GuardrailAgent, that offers adaptive, end-to-end protection. The system autonomously gathers and summarizes attack characteristics into a continuously updated knowledge base that supports both input- and output-side detection. A feedback module integrates misclassified cases for iterative improvement at minimal cost. Tested on over ten representative jailbreaks, the framework achieved a 93.1% input-side detection rate, 93.9% overall detection, and a 95.8% F1 score, while rapidly adapting to unseen attacks. These results demonstrate GuardrailAgent's outstanding capability to maintain LLM safety in the face of evolving jailbreak tactics.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09728

SAGE-PAIR: Source-Pretrained Routed Residual Adaptation for Sparse-Feedback Recommendation

Weiqing Zeng, Zida Yang, Guquan You, Jiexin Zheng, Cong Wang

原文摘要

Recommendation systems often enter a new serving window before enough outcomes are available to retrain the deployed model. We study this regime with 0.05-1.0% target feedback, a range that spans our stress tests while keeping supervision far below the degrees of freedom of the source recommender. At this scale, existing fine-tuning and meta-learning methods still estimate target-specific updates from extremely sparse feedback, leaving the update direction weakly identified. SAGE-PAIR instead transfers a source-supported residual correction space and only calibrates this space using target outcomes. We introduce SAGE-PAIR, a staged adapter that pretrains a low-dimensional global residual on an adjacent source period and adds a soft router over residual experts conditioned on source user profiles. Target feedback then calibrates this residual state rather than relearning the recommender. On a locked test split of KuaiSAR-v2, SAGE-PAIR (Full) achieves a 1.77% relative improvement in NDCG@10, while a core-protocol comparison shows a further 0.25% gain from routed experts beyond source-pretrained PAIR. Matched source-pretrained LoRA and Adapter-Tuning baselines remain near the source model, supporting the need for a different adaptation space. Thus, SAGE-PAIR improves ranking quality with millisecond-scale adaptation and inference costs. Sparse-feedback adaptation is fundamentally governed by the identifiability of the update space rather than by label count alone. Source pretraining supplies estimable correction directions for scarce labels, while user-conditioned routing contributes a consistent, differentiated cross-user correction on top of the global correction. Our code is available at https://anonymous.4open.science/r/SAGE-PAIR-610E/.

cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.09630

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models

Lin Zheng, Vasilisa Bashlovkina, Timothy Dozat, Dan Garrette, Laura Rimell, Joshua Maynez

原文摘要

Tokenizer-free language models eliminate the tokenizer step of the language modeling pipeline by operating directly on bytes; patch-based variants further aggregate contiguous byte spans into patches for efficiency. However, the average patch size chosen at the model design stage governs a tight trade-off: larger patches reduce compute and KV-cache footprint, but degrade modeling quality. We trace this trade-off to patch lag: until a patch is fully observed, byte predictions within it must rely on a stale representation from the previous patch to preserve causality; this lag widens as patches grow larger. We introduce Scratchpad Patching (SP), which inserts transient scratchpads inside each patch to aggregate the bytes seen so far and refresh patch-level context for subsequent predictions. SP triggers scratchpads using next-byte prediction entropy, selectively allocating compute to information-dense regions and enabling post-hoc adjustment of inference-time compute. Across experiments on natural language and code, SP improves model quality at the same patch size; for example, even at $16$ bytes per patch, SP-augmented models match or closely approach the byte-level baseline on downstream evaluations while using a $16\times$ smaller KV-cache over patches and requiring roughly $3$-$4\times$ less inference compute than the byte-level baseline.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09723

Fixed-point acceleration on Neural Wasserstein manifolds

Vitalii Aksenov, Sebastian Gutierrez Hernandez

原文摘要

We propose a fixed-point acceleration method for optimization over probability measures, applicable to a variety of machine learning problems. We represent probability measures as pushforwards of a reference distribution through a neural network map and equip the parameter space with the induced pullback Wasserstein metric. This geometric structure allows natural gradient descent to be interpreted as a fixed-point iteration on a Riemannian manifold. We accelerate this iteration using Riemannian Anderson mixing method, which exploits historical residuals to capture approximate second-order information without forming Hessians. In the present parametric setting, the manifold is represented by Euclidean coordinates endowed with a point-dependent metric, simplifying retraction and vector transport. We evaluate the method on multimodal sampling, PDE-based inverse problems, aggregation dynamics, Bayesian logistic regression, and generative modeling. Across the tested tasks, Anderson mixing reduces the number of natural-gradient iterations and achieves competitive performance relative to SGD and Adam in terms of both loss-gradient evaluations and wall-clock time. These results suggest that fixed-point acceleration is an efficient tool for improving the computational efficiency of training on parametric Wasserstein methods.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09722

FOSCAR: Accelerating Decode Attention over 2- and 4-Bit KV Caches through Affine Folding

Donglin Zhuang, Pragaash Ponnusamy, Xiaoxia Wu, Shuaiwen Leon Song, Zhongzhu Zhou

原文摘要

Large-language-model decode attention streams the key-value (KV) cache for every generated token. Packing that cache into 2-bit or 4-bit quantized integers reduces memory traffic but does not automatically translate into latency saving. Existing 2-bit fused kernels reach under 31%/15% of peak HBM throughput on H100/B200. Converting each value and applying its scale and offset before feeding Tensor Cores is a major bottleneck because instruction-issue throughput is scarce on modern GPUs. Instead of applying scale and offset to each KV value, FOSCAR uses affine folding to apply them to the other operand or the output of decode-attention matrix products, depending on the quantization scheme (token-wise or channel-wise). This reduces scale-and-offset operations by up to two orders of magnitude while preserving the dequantized attention output in exact arithmetic. FOSCAR also uses bit manipulation to feed KV operands to Tensor Cores efficiently, requiring only 1 and 0.19 ALU instructions per INT2 element on H100 and B200, respectively. Finally, FOSCAR builds warp-specialized GPU pipelines for Hopper (H100) and Blackwell (B200) using wgmma and tcgen05. On H100, FOSCAR INT2 and INT4 kernels achieve geo-mean speedups of $3.36\times$ and $2.83\times$ over FlashInfer BF16, and $2.03\times$ and $1.71\times$ over TensorRT-LLM FP8. On B200, the corresponding INT2 and INT4 speedups are $2.67\times$ and $2.30\times$ over FlashInfer BF16, $1.48\times$ and $1.28\times$ over TensorRT-LLM FP8, and $1.16\times$ and $1.00\times$ over TensorRT-LLM NVFP4. We integrate FOSCAR into SGLang to benchmark serving efficiency. On long-context serving workloads, FOSCAR increases peak aggregate throughput by up to 170% and 341% over 2-bit and 16-bit baselines, respectively. We open-source FOSCAR as a kernel library at https://github.com/FutureMLS-Lab/FOSCAR.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09721

MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory

David H. Yang, Blake Bullwinkel, Amanda Minnich, Mohammad Mohammadi Amiri, Giorgio Severi

原文摘要

LLM agents benefit from using memory systems to improve performance on long-horizon, multi-session tasks. However, memory introduces a critical attack surface. Malicious instructions encountered in one session may be stored and propagated through memory before being retrieved and acted upon in later sessions. Because memory systems differ in how they process and retrieve information, the downstream effects of poisoning can vary significantly across systems. To quantify the effects of poisoning across different memory architectures, we introduce MemoryDojo, a benchmark for tracing the lifecycle of poisoned information through agent memory and measuring its influence on subsequent agent behavior. MemoryDojo is easily extensible, consists of 155 multi-session long-horizon trajectories covering four domains, and supports five different memory systems. Through our evaluation, we find that all memory systems are susceptible to memory poisoning, with substantial variation in downstream effects. We further propose a memory-aware poison optimization process that increases the poisoning efficacy, highlighting differences between memory architectures. We hope that MemoryDojo will support research on understanding and mitigating agentic memory risks.

cs.CR · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2407.16897

HexTiles and Semantic Icons for MAUP-Aware Multivariate Geospatial Visualizations

Yuya Kawakami, Sarah Yuniar, Kwan-Liu Ma

原文摘要

We introduce HexTiles, a hexagonal-tiling based visual encoding design for multivariate geospatial data. Visualizing several geospatial variables at once is difficult because map position is already reserved for geography, and because variables are often reported on different, irregular spatial units whose aggregation is subject to the Modifiable Areal Unit Problem (MAUP). HexTiles bins data of differing spatial discretizations into hierarchical hexagons and encodes up to three variables per tile in a base color, an inner ring, and semantic icons whose count conveys value, letting the visualization designer guide attention to specific variables and their interactions. To make the effects of MAUP visible, we compute a spatially-weighted variance for each variable within each tile and encode it as a confidence value in every channel, so that the variability hidden by aggregation is not lost. Because interactive maps are increasingly viewed in tilted, 3D perspective, HexTiles encodes quantitative values only in channels that perspective does not distort, namely color and icon count. In a user study comparing HexTiles to Square-glyphs, participants rated HexTiles as significantly less demanding and frustrating, and performed more consistently with it. Domain experts in ecology and hydrology further noted its value for communicating regional patterns, and that the confidence encoding signals where aggregated values should be interpreted with care. Our results suggest that, although 3D is commonly discouraged, it can work for multivariate geospatial visualization when restricted to perspective-robust channels.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.26935

DunbaaBERT: From Sacrifice to Semantics

Iffat Maab, Waleed Jamil, Raphael Schmitt

原文摘要

Large language models have achieved strong performance across many NLP tasks, yet Urdu remains comparatively underexplored due to limited resources and fragmented evaluation settings. To address this gap, we introduce DunbaaBERT, a family of Urdu RoBERTa-base models trained from scratch with Byte-BPE vocabularies of 32k, 52k, and 96k tokens on a deduplicated 17 GB Urdu corpus. We evaluate DunbaaBERT across intrinsic and downstream Urdu NLP benchmarks covering linguistic acceptability, news classification, offensive language detection, and sentiment analysis, while analyzing vocabulary-size effects on performance, pre-training dynamics, and computational efficiency. Across benchmarks, the DunbaaBERT variants achieve competitive performance against strong multilingual baselines while consistently maintaining favorable efficiency trade-offs. Under our controlled experimental setup, increasing the vocabulary size does not consistently improve downstream effectiveness, with DunbaaBERT$_{32k}$ repeatedly providing the strongest overall efficiency profile. Overall, our results demonstrate that carefully curated Urdu-specific encoder models can remain highly competitive despite comparatively compact model and training scales. All models are released under the MIT license.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09715

Intent-Aware Caching for Efficient LLM Serving

Kazi Hasan Ibn Arif, JinYi Yoon, Dimitrios S. Nikolopoulos, Hans Vandierendonck, Deepu John, Bo Ji

原文摘要

Modern LLM serving systems use prefix caching to accelerate multi-turn conversational workloads. They cache the key-value states of previous conversation prefixes and reuse them when subsequent requests share the same prefix, to avoid redundant prefill computation and reduce serving latency. However, achieving a high cache hit rate remains challenging because cache reuse depends on whether a conversation continues and how soon the next turn arrives. Our analysis of real workloads shows that user intent is a useful signal for this behavior, as different intents exhibit different continuation probabilities and inter-turn delays. Based on this key insight, we propose Intent-Aware Caching (IAC), an online eviction policy that classifies requests by intent, learns lightweight reuse statistics from recent serving logs and leverages these statistics to guide an oracle-inspired eviction strategy. Extensive evaluation on real workloads (WildChat and ShareChat) shows that IAC reaches a 34.6% cache hit rate. This substantially outperforms both the previous learning-based approach (18.8%) and traditional methods such as least recently used (LRU, 12.2%), while reducing average serving latency by up to 46.1%.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09714

Beyond Segmentation: Enriching ImageCAS with Coronary Ostia Landmarks, Rooted Centerline Graphs, and Open-Weight Localization Models

Matteo Leccardi, Andrea Moglia, Marco Morandini, Michele Brembilla, Alessandro Nicosia, Andrea Penserini, Christian Brandini, Ender Konukoglu 等 11 位作者

原文摘要

Coronary ostia and centerlines are key reference points for automated analysis of coronary computed tomography angiography (CCTA), from surgical planning to intraoperative vessel tracking. However, the only public ostium annotations cover 77 non-gated aortic scans, not CCTA, while CAT08 and ASOCA (32 and 40 CCTA scans) mark the ostia only implicitly, as centerline start points. This work enriches ImageCAS, the largest public dataset for coronary artery segmentation, with ostium annotations for its 1000 patients and centerline graphs rooted at these new ostia, making it, to the authors' knowledge, the largest public dataset for ostium localization and the only one with centerlines following the official ImageCAS masks and starting at annotated ostia. Three annotators marked each ostium in the first 500 volumes; in the next 500, the candidates of a model trained on the first batch were corrected (human-in-the-loop). Six 3D localization models, trained on ImageCAS, CAT08 and ASOCA, were benchmarked on 58 held-out volumes (50 ImageCAS, 4 CAT08, 4 ASOCA). SwinUNETR-V2 and nnResUNet localized all ostia without failure (>5 mm error), with median errors of 0.70-0.87 mm. Trained on CAT08 and ASOCA alone, SwinUNETR-V2 fails on 34% of right and 53% of left ostia, whereas adding 250 ImageCAS volumes removes all failures. The centerlines were extracted by a deterministic, quality-controlled minimal-path procedure; on ASOCA, they cover a median of 99.5% of the reference length, with a median per-patient mean distance of 0.22 mm between matched reference points and centerlines. Annotations, centerlines, code, and weights are available at https://hal9000-lab.github.io/.

eess.IV · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09712

ICare-DT: a digital twin for continuous forecasting of intensive care patients

Yanke Li, Yahang Qi, Yumi Kim, Diego Paez-Granados

原文摘要

Digital twins of intensive care patients should update forecasts from new data and predict treatment responses, but few studies test whether routine records support either. We propose ICare-DT, a Transformer-based twin that updates a latent patient state hourly from new measurements without retraining. We trained it on 140,473 eICU-CRD stays to forecast vital signs crossing their training-set means. On test data, later forecasts beat the twin's own hour-6 forecasts of the same windows in all 12 settings (+0.073 to +0.153 AUROC). On validation data, controls that withheld or swapped the new hours traced the gain to the patient's own measurements. Without refitting, the model kept its gain on a second database (8 of 9 settings, +0.025 to +0.114 AUROC) in a prespecified evaluation of the previously analyzed MIMIC-IV test split. Refitted within MIMIC-IV, a twin state fine-tuned on clinical endpoints gave gradient boosting a significant gain for acute kidney injury (+0.0035 AUROC; hypotension +0.0010, not significant). To test response prediction, we built a benchmark that replaces the treatments in real records with simulated doses and injects responses of known size, visible only at measurement times. Ridge models supervised with injected effects recovered them from real records only through frequently measured variables (heart rate) read at their measurement times. We asked standard learners to predict these effects for a dosing regime no patient had received. No standard learner outperformed predicting zero effect at an out-of-support query. When told how the simulated responses were generated, a separate learner recovered the effects from the same records without seeing their true values (R2 0.30 to 0.40 at one effect size). Routine records support forecasts that improve with each patient's new data, and our benchmark is a testbed for models that learn how responses are generated.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.05026

Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models

Bartlomiej Sobieski, Matthew Tivnan, Michał Jan Włodarczyk, Dawid Płudowski, Pengfei Jin, Przemyslaw Biecek, Quanzheng Li

原文摘要

Diffusion models are prone to generating structural hallucinations - samples that match the statistical properties of the training data yet defy underlying structural rules, resulting in anomalies like hands with more than five fingers. Recent research studied this failure mode from several viewpoints, offering partial explanations to their occurrence, such as mode interpolation. In this work, we propose a complementary perspective that treats hallucinations as instabilities on the model-induced manifold. We begin by showing that a hallucination filter based on such instabilities matches or exceeds the performance of the recently proposed temporal one. By tracing the source of these instabilities, we identify local intrinsic dimension (LID) as their primary driver and propose Intrinsic Quenching (IQ), a direct corrective mechanism that deflates it to alleviate hallucinations. IQ consistently outperforms standard hallucination reduction baselines across a wide array of benchmarks and offers a highly promising solution for enforcing anatomical consistency in downstream medical imaging tasks.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09709

RidgeFill: Training-Free Late-Layer Cache Fill for Faster Prefill

Dylan Johnston, Robert P. Smith

原文摘要

RidgeFill shortens prefill by not computing most of a model's upper layers for the prompt. The lower layers run exactly up to a split; from the split layer's state a per-layer map predicts every later layer's input, and each late layer writes its cache from that prediction. The design follows YOCO and DeepSeek-V4.1-Flash, where the projection is trained into the model. RidgeFill retrofits it onto models that were never trained for it: the map is a ridge regression fitted once in closed form from one pass over calibration text, the layer's own projections run unchanged, and a chosen set of rows, the last few thousand tokens, and every decoding step run the full model. Nothing is trained and no token is dropped. Most of the work was in measurement, finding a repeatable methodology. Loss averaged over all tokens hides RidgeFill's error. Needle retrieval in the filled region, loss on tokens that depend on distant context, and splice tests that swap filled keys or values for exact ones show which component carries it: the keys on Llama-3.1-8B, half of it in their scale, and the values and the recurrent state on Qwen3.5-9B. On Qwen3.8-27B in a llama.cpp fork on an A100, time to first token is 1.25 to 1.31x faster at 16K to 120K tokens with the maps in VRAM; RULER changes by -1.2 and -1.4 points and LongBench v2 by -1.4; the 95 % intervals include zero but do not rule out losses of a few points. On Qwen3.8-Flash-Next in vLLM it is 1.50 to 1.60x faster than exact at 9K to 32K tokens, with RULER's needle tasks at 99.8 against 100.0 and perplexity on novel tokens 2.65 % higher [-0.02 %, +4.93 %]. On three 8 to 9B reference models, at the same split and tail as the identity fill, the fitted map retrieves 49.1 and 49.6 more filled-region RULER points on the two dense models (at that split Llama's loss is worse), and its long-document loss is +/-0.03 nats of the released SwiftKV checkpoint's.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02780

Lookahead Prediction-Guided Adaptive Visual Refocusing for Interleaved Multimodal Reasoning

Mengzhao Wang, Yanli Ji, Peng Ye

原文摘要

Interleaved multimodal chain-of-thought reasoning improves the visual reasoning capabilities of multimodal large language models by dynamically incorporating visual evidence during reasoning. However, existing methods primarily select evidence from historical context. When the reasoning focus shifts, history-guided evidence may remain focused on prior regions and fail to cover the visual information required by the next step. We refer to this lag between visual evidence and subsequent reasoning demands as Temporal Evidence Myopia. To address this issue, we propose Lookahead Prediction-guided Adaptive Visual Refocusing (LPAVR), a training-free test-time framework. LPAVR transforms Multi-Token Prediction (MTP) from a decoding acceleration mechanism into a lookahead signal for anticipating upcoming reasoning intent. During MTP decoding, the draft head generates multiple future tokens, while the target model verifies them in parallel and retains the longest prefix consistent with its decoding trajectory. This target-verified prefix contains near-future semantics, which LPAVR uses to construct lookahead-guided visual evidence and assess whether history-guided evidence covers the indicated regions. If the coverage is sufficient, the history-guided evidence is retained; otherwise, LPAVR switches to the lookahead-guided evidence. This better aligns the visual context with upcoming reasoning and improves consistency between draft predictions and target-model decoding. Experiments on multiple multimodal reasoning benchmarks show that LPAVR improves both reasoning accuracy and the acceptance rates of MTP speculative tokens, jointly enhancing visual reasoning and speculative decoding efficiency.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.18127

Predictive Representation Learning for Manipulation via Streaming Egocentric 3D Hand Forecasting

Ruicong Liu, Yifei Huang, Liangyang Ouyang, Caixin Kang, Yoichi Sato

原文摘要

Learning embodied manipulation from egocentric human data offers a scalable path, reducing the cost of collecting robot-specific demonstrations. However, existing representation learning methods largely stop at perceptual understanding, such as extracting what a scene contains or what an action is. A capable embodied agent is more than understanding: it predicts the next motion. We propose that forecasting 3D human hand motion is one suitable pretraining task, as the representation jointly learns how to manipulate objects and how the motion will unfold next. Building on this hypothesis, we introduce SFHand, the first representation learning method via streaming egocentric 3D hand forecasting. SFHand learns by autoregressively predicting future 3D hand states, including hand type, 2D bounding box, 3D pose, and trajectory, from a continuous stream of video and language instructions. Its autoregressive architecture is equipped with an ROI-enhanced memory layer, capturing temporal context while focusing on salient hand-centric regions. To enable this research, we also introduce SFHand, the first open-source large-scale dataset pairing synchronized 3D hand poses with fine-grained language instructions (247K clips, 3.95M frames). Transferred to downstream embodied control, the learned representation shows state-of-the-art performance on both simulation and real-world manipulation benchmarks, improving success rate by up to 13.4%. Our method also achieves leading 3D hand forecasting accuracy, with 35.8% lower ADE than baseline methods. These results suggest that forecasting hand motion is a better pretraining task for representation learning in embodied manipulation. Projec page: https://ruicongliu.github.io/sfhand/.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09708

A wearable input/output interface learns personalized models of haptic perception

Wen Li, E. Magnus Adams, Zijie Xu, Jiawen Yao, Aybala Esmer, Xiaoyue Ni, Bozhi Tian, Pedro Lopes

原文摘要

Wearable haptic interfaces deliver physical stimuli to the skin, yet perceived locations vary widely across users and diverge from actuator locations, particularly for emergent tactile-feedback techniques. We developed a wearable haptic input/output (I/O) device integrating a 36-channel electrotactile array with capacitive touch sensing, enabling stimulation and user-reported percept locations to be registered within the same body-referenced coordinate frame. In 24 participants, the device revealed electrotactile and referred-thermal perceptual maps with notable interparticipant variability. Despite this variability, both modalities retained electrode-pair-specific spatial structure across participants. Tactile and thermal percepts also showed spatial correspondence, whose strength varied across participants. These findings motivated our human-in-the-loop calibration framework, which adapts a forward-prediction strategy to individual users and generates personalized perceptual models. These models enabled inverse rendering by selecting stimulation patterns predicted to generate a target percept for a specific user. Using these models, we demonstrate personalized haptic rendering in haptic-guided robot teleoperation, visual-to-haptic sensory substitution, interpersonal haptic communication, and virtual reality (VR). Together, this platform provides a route toward adaptive haptic interfaces that measure, model, and render according to each user's perception.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09707

Empirical Assessment of Post-Quantum Cryptography Adoption Status in TLS

Md Ariful Haque, Sander Vinberg, Ben Edwards, João Cruz

原文摘要

Anticipating Q-day security concerns, major CDNs and cloud providers are migrating to post-quantum cryptography (PQC). While existing literature benchmarks PQC performance, empirical research evaluating real-world adoption data remains scarce. We present an empirical assessment of PQC deployment across seven critical protocols (HTTPS, LDAPS, SMTPS, IMAP-SSL, POP3-SSL, TELNETS, and RDP) using 10,000 target IP addresses per protocol. At the origin-server level, PQC algorithm support reaches 9.1% for HTTPS and 7.39% for LDAPS, while falling below 1% for all other evaluated protocols. At the entity level, PQC support is 11% for HTTPS and 5.4% for LDAPS, while the remaining protocols have less than 5% of entities supporting PQC on the hosted servers. We further correlate these adoption trends against organizational digital and financial footprint, and industry sectors, yielding a multi-dimensional empirical assessment of PQC deployment. Finally, at the domain level, we perform a comparative analysis of PQC adoption in Cloudflare-hosted domains against baseline Cloudflare datasets. Collectively, our findings provide critical insights into the current state of PQC readiness over Transport Layer Security (TLS).

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.10984

Sample Efficient Generative Molecular Optimization with Joint Self-Improvement

Serra Korkmaz, Adam Izdebski, Jonathan Pirnay, Rasmus Møller-Larsen, Michal Kmicikiewicz, Pankhil Gawade, Maksim Pavlov, Dominik G. Grimm 等 9 位作者

原文摘要

Generative molecular optimization aims to design molecules with properties surpassing those of existing compounds. However, evaluating candidate molecules is expensive, so sample efficiency, i.e., generating optimized molecules within a fixed evaluation budget, is essential. Moreover, in the offline setting, where a surrogate model approximates candidate evaluation, sample inefficiency compounds with surrogate error, further limiting performance. To address these challenges, we introduce Joint Self-Improvement (JSI), a framework for sample-efficient online and offline molecular optimization. JSI combines (i) a joint generative-predictive model trained via a joint likelihood-based loss, which aligns molecule generation and surrogate modeling, and (ii) inference-time self-improvement, which iteratively biases the generative component of the joint model toward higher-scoring molecules, using direct objective function evaluations in the online setting and the predictive component in the offline setting. Experiments across docking score optimization in both online and offline settings, as well as antimicrobial peptide optimization, demonstrate that JSI outperforms state-of-the-art methods under limited evaluation budgets. Code is available at https://github.com/szczurek-lab/jsi.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09700

Attend at the Right Resolution: Head-Adaptive Sparse Attention via Query-Key Interaction Structure

Wajih Hassan Raza, Ahsan Bilal, Yidan Shen, Renjie Hu, Xin Fu, Yu Wen

原文摘要

Attention is a major scalability bottleneck in large language models (LLMs), with its computational cost and key-value (KV) memory traffic becoming increasingly prohibitive as context length grows. Sparse attention addresses this bottleneck by restricting each query to a subset of the context, but its effectiveness hinges on identifying relevant regions both cheaply and reliably. Existing training-free methods primarily rely on runtime relevance estimates, with selection dimensionality and granularity typically governed by fixed heuristics rather than the intrinsic interaction structure of pretrained attention heads. We take a different perspective: the query-key operator of each pretrained head defines a characteristic response structure that determines the resolution needed for sparse selection, both across feature directions and across context tokens. Building on this insight, we propose Head-Adaptive Sparse Attention (HASA), a training-free sparse attention framework that jointly adapts selection resolution along these two dimensions. Along the feature dimension, the singular spectrum of each head's query-key operator determines an effective rank, yielding a compact, head-specific response space. Along the sequence dimension, neighboring regions are progressively merged according to the directional coherence of their token responses in this same space, while heterogeneous regions remain separate. Exact attention is then computed using the original full-dimensional KV states of the selected regions. HASA captures 88.1% of dense-attention mass and, compared with UNIQUE, a strong recent sparse-attention baseline, improves accuracy by up to 3.47 and 2.57 points on RULER and LongBench-Pro, respectively, and accelerates self-attention by up to 1.32x, while achieving up to 14.07x speedup over dense attention.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09699

Verifier Noise Is a Temperature: Testing Tilt Predictions in Finite-Budget LLM-Guided Search

Xiaomeng Li

原文摘要

LLM-guided search loops propose a modified candidate, score it, and keep it if it scores better. When both candidates are re-scored at every comparison, as in the minibatch acceptance gates of prompt optimizers, keep-if-better is a reversible Markov chain if the score difference is logistic and the mutation operator is reversible, and its stationary law is the mutation equilibrium tilted by exp(beta f). For any continuous symmetric noise difference the same tilt is the stationary law of a small-step diffusion limit, with beta = 4F'(0); for a minibatch gate beta grows with the square root of the minibatch size. Caching the incumbent's score instead inflates the recorded score. We test the tilt as a prediction for LLM-guided program search, committing each prediction from calibration data before the search runs. The level after 150 steps rises with the minibatch size in six of seven settings, but its predicted value fails: on bin packing, search attains 62-88% of the predicted gain when the proposer edits the parent and 109-119% when it writes new heuristics. The attained fraction falls with the parent-child quality correlation of unselected mutation; a registered test on two new settings confirmed the direction, but not the quantitative agreement after a correction. Further registered tests found that runs started from a good program kept losing quality over 300 steps, more so from starts that search had selected, by a margin that passed its registered rule narrowly. Runs from different starts had not reached a common level, so whether the tilt describes the stationary law of LLM editing remains open. A registered test in prompt optimisation on frozen task-model scores failed: search exceeded the tilt, and the bin-packing relation did not transfer.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.12736

Aïra: Rethinking AI Research Assistants for Interdisciplinary Science

Diya Mirji, Tiffany Degbotse, Sharmil Nanjappa, Jiayi Zhou, Vishnu Manoj, Vihaan Nama, Boyuan Chen, Lee Tiedrich 等 12 位作者

原文摘要

Scientific discovery increasingly depends on interdisciplinary teams whose members contribute distinct expertise, conceptual frameworks, vocabularies, assumptions, and standards of evidence. Today's AI research assistants are largely designed to support individual researchers through literature review, writing assistance, coding, and data analysis. While these capabilities improve personal productivity, they provide little support for the collaborative reasoning required to integrate knowledge across disciplines. In this vision paper, we argue that AI research assistants should evolve from tools that optimize individual workflows to systems designed for interdisciplinary teams. We introduce aïra, an AI research assistant built around this idea. Rather than focusing solely on summarization or question answering, aïra identifies disciplinary perspectives, translates terminology, highlights assumptions, and synthesizes collaborative research opportunities. This paper offers a vision describing the design principles underlying aïra, presenting its system architecture, illustrating its outputs through interdisciplinary research meetings, and outlining future research directions for AI systems that support collaborative scholarship.

cs.HC · cs.MA

查看论文
arXiv ↗PDF ↗