Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
PLOS Medicine 2026-06-23

Comparisons of core component delivery in cardiac rehabilitation programs by country income classification and decade based on the 2025 Global Audit Update: A survey study

by Gabriela Lima de Melo Ghisi, Rachael P. Carson, Karam Turk Adawi, Rongjing Ding, Warner M. Mampuya, Mariya P. Jiandani, Jimena Martinez, Monserrat Cruz Rivero, Claudia V. Anchique, Dinah L. van Schalkwijk, Jonathan Gallagher, Buket Akinci, Dion Candelaria, Jirapa Champaiboon, Daniel F. Quesada-Chaves, Tone M. Norekvål, Iwona Szadkowska, Borut Jug, Evangelia Kouidi, Marta Supervia, Won-Seok Kim, Chamila Mettananda, Lilian Mbau, Gulsim T. Aimakova, Sherry L. Grace, on behalf of the ICCPR Global Cardiac Rehabilitation Audit Update Investigators Background Cardiovascular disease (CVD) remains a leading global health burden. Cardiac rehabilitation (CR) is essential to reducing morbidity and improving patient outcomes. Since the COVID-19 pandemic, CR delivery worldwide has evolved, yet these changes have not been systematically charactemkjrized. The objective of this study was to characterize globally: (1) the delivery of core CR components, including risk factors assessed, patient education practices, and program resources; (2) differences in these elements by country income classification and relative to the initial 2016 Global CR Audit. Methods and findings A cross-sectional Audit update was conducted. Program-level data were collected from May 1st to September 1st 2025 using a REDCap survey adapted from previous Audits. Eligible respondents were leads of phase II/post-discharge CR programs providing at least an initial assessment, structured aerobic exercise, and ≥1 additional core component. ICCPR associations and local leaders supported program identification. Main outcomes were core components delivered (10 assessed), risk factors assessed (14 assessed), patient education dose (hours/patient/program), and program resources (17 assessed). Generalized linear mixed models (GLMM) tested differences by income classification and (when applicable) changes since 2016. Of 7,025 programs identified globally, 1,505 (62% median country response rate) initiated a survey from 90/113 (80%) countries with CR. The median number of core components offered was 8/program (p25, p75 = 6, 10), with upper-middle income countries offering significantly more components overall (median = 9), and also high-income countries offering more than low-income countries (8 versus 6, p 

02.
arXiv (math.PR) 2026-06-16

Atypical Decay Rates for Atypical Heights in Random Recursive Trees

arXiv:2604.20139v2 Announce Type: replace Abstract: We establish the large deviation probabilities for the height of random recursive trees, revealing polynomial upper-tail decay and stretched-exponential lower-tail decay. Remarkably, the lower tail features an atypical prefactor that grows to infinity more slowly than any $n$-fold iterated logarithm.

03.
arXiv (CS.CV) 2026-06-24

Automated Residual Plot Assessment With the R Package autovi and the Shiny Application autovi.web

Visual assessment of residual plots is a common approach for diagnosing linear models, but it relies on manual evaluation, which does not scale well and can lead to inconsistent decisions across analysts. The lineup protocol, which embeds the observed plot among null plots, can reduce subjectivity but requires even more human effort. In today's data-driven world, such tasks are well suited for automation. We present a new R package that uses a computer vision model to automate the evaluation of residual plots. An accompanying Shiny application is provided for ease of use. Given a sample of residuals, the model predicts a visual signal strength (VSS) and offers supporting information to help analysts assess model fit.

04.
arXiv (CS.CV) 2026-06-15

High-Fidelity Video Compression based on Invertible Neural Transform and Implicit Conditioning

Learning-based video compression has recently achieved competitive rate-distortion performance compared to conventional video codecs. However, most existing methods rely on non-invertible analysis-synthesis transforms, with reconstruction quality subject to both quantization and transform approximation errors. This limitation becomes particularly restrictive at higher quality points, where quantization errors are small and transform-induced distortion dominates. To address this, we propose InnVC, an Invertible neural network based Video Codec for wide-range and high-fidelity compression. The core idea is to preserve an invertible main transform path prior to quantization, while injecting content-adaptive context through a compact implicit conditioning field. This decouples strongly correlated video content from harder-to-model fine details, allowing different components to specialize in complementary reconstruction tasks for more efficient compression. To further improve compressibility, we introduce a scheduled masking strategy that progressively concentrates informative content into fewer latent channels for more effective entropy coding. Experiments on the UVG and MCL-JCV benchmarks show that InnVC achieves strong compression performance over a broad quality range, being particularly effective in the high-quality regime, yielding BD-rate reductions of 21.66% in PSNR and 46.06% in MS-SSIM relative to x265 on UVG. To the best of our knowledge, InnVC is the first neural video codec covers operating poins from low bitrate to high fidelity within a single architecture scale, spanning more than 20 dB in PSNR.

05.
arXiv (CS.AI) 2026-06-16

When Do We Need LLMs? A Diagnostic for Language-Driven Bandits

arXiv:2604.05859v2 Announce Type: replace Abstract: We study Contextual Multi-Armed Bandits (CMABs) for non-episodic decision-making problems where the context includes both textual and numerical information (e.g., recommendation systems, dynamic portfolio adjustments, offer selection; all frequent problems in finance). While Large Language Models (LLMs) are increasingly applied to these settings, utilizing LLMs for reasoning at every decision step is computationally expensive, and uncertainty estimates are difficult to obtain. To address this, we introduce LLMP-UCB, a bandit algorithm that derives uncertainty estimates from LLMs via repeated inference. However, our experiments demonstrate that lightweight numerical bandits operating on text embeddings (dense or Matryoshka) match or exceed the accuracy of LLM-based solutions at a fraction of their cost. We further show that embedding dimensionality is a practical lever on the exploration-exploitation balance, enabling cost-performance tradeoffs without prompt complexity. Finally, to guide practitioners, we propose a geometric diagnostic based on the arms' embeddings to decide when to use LLM-driven reasoning versus a lightweight numerical bandit. Our results provide a principled deployment framework for cost-effective, uncertainty-aware decision systems with broad applicability across AI use cases.

06.
arXiv (quant-ph) 2026-06-16

How Many Shots Are Enough for a Quantum Circuit?

arXiv:2606.16965v1 Announce Type: new Abstract: Quantum algorithms require repeated circuit executions, known as shots, to estimate output distributions accurately. Determining the minimal number of shots needed to meet a target accuracy is crucial to reduce costs and resource usage, especially on today's noisy and expensive quantum hardware. In this paper, we address the shot optimisation problem in a black-box setting, where no assumptions are made about the structure of the quantum circuit or the noise model of the backend. We introduce IncrementalExecution, a novel online framework that dynamically determines when to stop executing shots based on the principle of point of diminishing returns: the point at which additional shots no longer significantly alter the empirical distribution of a fixed circuit. The framework supports customisable policies for shot management, enabling flexible trade-offs between execution cost and result fidelity within static execution scenarios. We assess our proposal through an extensive experimental evaluation spanning 33,750 framework configurations across 180 unique static quantum circuit-backend combinations, for a total of 7.3M independent experiments. Unlike prior work that relies on problem-specific knowledge or algorithm-dependent assumptions (e.g., variational or adaptive workflows), our approach is applicable to a large set of static circuits and immediately deployable on current quantum cloud platforms.

07.
arXiv (CS.LG) 2026-06-15

Temporal Straightening for Latent Planning

arXiv:2603.12231v2 Announce Type: replace Abstract: Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual features, they are not tailored to planning and contain information irrelevant – or even detrimental – to planning. Inspired by the perceptual straightening hypothesis in human visual processing, we introduce temporal straightening to improve representation learning for latent planning. Using a curvature regularizer that encourages locally straightened latent trajectories, we jointly learn an encoder and a predictor of a Joint-Embedding Predictive Architecture (JEPA) world model. We show that reducing curvature this way makes the Euclidean distance in latent space a better proxy for the geodesic distance and improves the conditioning of the planning objective. We demonstrate empirically that temporal straightening makes gradient-based planning more stable and yields significantly higher success rates across a suite of goal-reaching tasks. Our code is available at https://agenticlearning.ai/temporal-straightening.

08.
arXiv (CS.AI) 2026-06-15

Numbers Already Carry Their Own Embeddings

arXiv:2606.14108v1 Announce Type: cross Abstract: We introduce Adelic operation-preserved embeddings (AOE), a training-free representation that captures both a number's real value and its modular (p-adic) signatures. This construction preserves additive and multiplicative structure by design, turning numerical input into embeddings that "speak in the language of mathematics." Unlike prior approaches that rely on task-specific retraining, AOE is plug-and-play and drops seamlessly into existing architectures. On algebraic combinatorics benchmarks, it delivers consistent gains including the first-ever perfect accuracy on the Weaving Pattern task-while suggesting a principled path forward for overcoming the long-standing "number problem" in AI.

09.
bioRxiv (Bioinfo) 2026-06-14

Generative design of antigen-specific T-cell receptor sequences with a conditional diffusion model

T cell receptor (TCR)-based immunotherapy holds immense potential for treating cancers and infectious diseases, where highly antigen-specific TCR recognition is crucial for adaptive immunity against tumors and pathogens. Engineering or de novo generation of the complementarity-determining region 3 (CDR3) loops of TCRs using artificial intelligence offers a powerful alternative to designing reactive TCRs rather than laborious experimental screening. However, current in silico approaches are constrained by weak conditional guidance, limited flexibility, and a lack of rigorous functional validation. To address these limitations, we introduce TCRDiff, a generative diffusion framework for designing antigen-specific TCRs conditioned on peptide-MHC (pMHC) targets and germline-encoded variable genes. By leveraging pre-trained knowledge from massive T-cell repertoires and TCR-pMHC recognition data, TCRDiff generates CDR3{beta} sequences with state-of-the-art fidelity to native binding TCRs through a denoising diffusion process. Furthermore, incorporating the interface geometry features generated TCR-pMHC complexes with superior structural plausibility. As a proof of concept, we deployed TCRDiff in a systematic pipeline to design candidate TCRs for immunotherapy. In vitro activation assays validated that TCRDiff-generated TCRs specifically recognize the MAGE-A3 epitope with minimized off-target cross-reactivity. Together, TCRDiff establishes a powerful, validated computational paradigm to accelerate the development of TCR-based immunotherapies.

10.
arXiv (CS.AI) 2026-06-16

CRC-Screen: Certified DNA-Synthesis Hazard Screening Under Taxonomic Shift

作者:

arXiv:2605.00074v2 Announce Type: replace-cross Abstract: DNA-synthesis providers screen incoming orders by searching the requested sequence against curated hazard lists. We show that this baseline collapses to a 100% false-flag rate when the hazardous sequence comes from a taxonomic family absent from the reference set: under Conformal Risk Control's certified miss-rate constraint, a low-discrimination signal forces the threshold below the entire test-benign mass. We compose three signals derived from a synthesis order's public annotation: $k$-mer Jaccard similarity to known toxins, the trimmed-mean score of a five-LLM judge panel, and cosine similarity to clustered embedding centroids. Fused under a monotone logistic aggregator and calibrated by Conformal Risk Control, the resulting screener certifies $\mathbb{E}[\mathrm{FNR}] \le \alpha + \mathrm{TV}$, where the additive term is the calibration-to-test distribution shift under family holdout (a certified ceiling of 24-49% across folds). Across ten leave-one-taxonomic-family-out folds at $\alpha=0.05$ on UniProt KW-0800 reviewed toxins, the calibrated screener achieves 0% empirical test miss rate on every fold and 0% test false-flag rate on nine of ten folds. The bound's finite-sample slack $1/(n_{\mathrm{cal}}+1)$ caps the certifiable miss rate at 1.77% on our 200-hazard subsample; reaching procurement-grade $\alpha=10^{-3}$ requires an $18\times$ larger calibration set, which the full reviewed UniProt KW-0800 corpus is large enough to deliver. The binding constraint on certifiable DNA-synthesis screening is calibration data, not algorithms. Code: https://github.com/najmulhasan-code/crc-screen

11.
arXiv (CS.AI) 2026-06-18

The More the Merrier: Combining Properties for ABox Abduction under Repair Semantics for ELbot

arXiv:2606.19197v1 Announce Type: cross Abstract: Abduction is a central approach to explain missing entailments from a knowledge base by providing a hypothesis, that would, if added to the knowledge base, make the missing entailment become true. Abduction under repair semantics has recently been investigated in detail, where several desirable properties and optimality criteria were considered, such as signature-restrictions and minimality in size and of introduced conflicts. Naturally, hypotheses that satisfy more than one of these properties or combine a property with an optimality criterion would be even more desirable for applications. So far, such hypotheses have not been investigated in the literature. In the present paper, we consider the ABox abduction problem for hypotheses satisfying more than one property or additional optimality criteria, for EL_bot under brave and AR semantics. Our main observation is that often requiring additional properties for hypotheses does not lead to an increase of complexity.

12.
medRxiv (Medicine) 2026-06-22

Paired plasma and EV-enriched plasma proteomics reveal nonredundant sepsis-associated host-response signatures in critical illness

Background: Plasma proteomics may identify host-response signatures in sepsis, but it is unclear whether extracellular vesicle (EV)-enriched plasma provides distinct or redundant information compared with plasma. We compared paired plasma and EV-enriched plasma proteomes in critically ill patients with sepsis and critically ill non-sepsis controls (CINS). Methods: In this prospective observational study, paired plasma and EV-enriched plasma samples were analyzed from 56 critically ill adults, including 40 patients with sepsis and 16 CINS patients. Protein abundance was quantified using liquid chromatography-tandem mass spectrometry. Analyses compared proteomic depth, protein overlap, global concordance between compartments, and differential protein abundance between CINS and sepsis. Exploratory Gene Ontology enrichment was performed as a supplementary analysis. Results: EV-enriched plasma expanded proteomic detection, identifying 2,476 filtered proteins compared with 506 in plasma. Only 386 proteins were detected in both compartments, while 2,090 were unique to EV-enriched plasma and 120 were unique to plasma. Among shared proteins, plasma and EV-enriched plasma showed modest global concordance across critically ill patients (Spearman coeff = 0.322, p = 9.19 x 10^-11), with similar findings in sepsis alone. Differential abundance analysis identified 11 sepsis-associated proteins in plasma and 22 in EV-enriched plasma. Only SAA1, SAA2, and IGFBP6 were significant in both compartments. Exploratory pathway analysis supported acute-phase and inflammatory enrichment in plasma sepsis-associated proteins, while EV-enriched signals were directionally plausible but did not meet prespecified FDR thresholds. Conclusion: Plasma and EV-enriched plasma proteomics capture related but nonredundant sepsis-associated host-response information in critically ill patients.

13.
arXiv (CS.AI) 2026-06-16

Looking Is Not Picking: An Attention-Segment Account of Tool-Selection Failures in LLM Agents

作者:

arXiv:2606.16364v1 Announce Type: new Abstract: LLM agents mis-call tools, and the natural guess is that the model failed to see the right tool in a crowded harness. We show the opposite through a lens concurrent work sets aside – the model's attention to labeled tool-definition segments. On real BFCL failures, by per-candidate attention argmax the model attends most to the correct tool 80% of the time (vs. 21% chance), and the gold is the under-attended segment on only 10%: it looks at the right tool and still picks wrong. This directly refutes the intuitive "crowded-harness / lost-in-the-middle" explanation: the failure is at the decision readout, not the harness, and we pin it there three ways. (1) Input vs. readout: repairing the prompt (reordering or duplicating the gold tool) recovers

14.
arXiv (CS.AI) 2026-06-15

tap: A File-Based Protocol for Heterogeneous LLM Agent Collaboration

作者:

arXiv:2606.14445v1 Announce Type: cross Abstract: Existing multi-agent software development systems have proposed many forms of agent collaboration, including role-based collaboration and automated code review. However, many systems assume a common runtime, a central conversation server, or the same API family. Under these assumptions, LLM agents from different vendors cannot easily exchange messages directly from their own execution environments while dividing development and review work on a shared codebase. This paper presents tap, a file-based collaboration protocol that allows Claude (Anthropic) and Codex (OpenAI) to collaborate on one codebase without shared memory or an identical runtime. The core of tap is a file-first design that preserves markdown files with metadata as original messages, combines a file inspection path (file communication, Tier 1) with real-time notification paths for Claude and Codex (real-time communication, Tier 2), and isolates work through separate git worktrees. Even if real-time notification fails or a receiver restarts, the message file remains available and the same content can be inspected again. In a 27-day, 37-generation self-applied operation where tap was used to develop and review itself, we collected 209 tap-related pull requests and 717 operational artifacts. An analysis of 375 review artifacts showed that the share of reviews recording at least one defect or requested change was 69.8% for heterogeneous model pairs and 53.1% for homogeneous model pairs. These results show that tap, which combines file-based message preservation with real-time notification, operates in a real production repository, and that combining heterogeneous models and execution environments can broaden review perspectives. tap is distributed as the open-source npm package @hua-labs/tap (v0.5.2).

15.
arXiv (CS.CL) 2026-06-16

Vernier: Probing Representational Misalignment Behind Lexical Gaps in Causal Reasoning

作者:

Instruction-tuned language models can answer the same causal-reasoning question differently after its English variable names are replaced by type-preserving placeholders, although the structural causal model and the gold answer are unchanged. We ask whether this lexical gap reflects information loss in the placeholder view or a misaligned read-out from a representation that still carries answer-relevant content. Vernier uses a paired-view weight update as an instrument and then inspects the mechanism left after the gap closes. In the working regimes, the evidence favours representational misalignment. A variable-name probe becomes more accurate on the placeholder view, and activation patching on Qwen-7B, Qwen-14B, and Llama-3.1-8B shows that the decision-token representation can transfer answer identity between views. The update that realigns the views is counterfactual augmentation over original and placeholder prompts, while the answer-subspace KL mainly sharpens intermediate answer-belief agreement. Success is bounded by model family, scale, and task. CRASS transfer is reliable across Qwen scales and Llama, e-CARE remains weak, and preliminary non-causal rename tasks show a similar qualitative pattern.

16.
arXiv (CS.CV) 2026-06-12

Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration

The rapid growth of modern training datasets has significantly increased computational cost, motivating dataset pruning~(DP) methods which retain only a subset of informative samples to reduce training cost. Existing pruning criteria typically rely on either intrinsic signals that assess samples independently or extrinsic signals that promote diversity via pairwise relations. While effective in their own specific regimes, each captures only one aspect of sample utility and lacks robustness across different pruning ratios or data distribution. In this work, we present a unified graph-based DP framework. By modeling the dataset as a weighted graph, where node weights encode intrinsic value and edge weights encode extrinsic value, DP can be cast as a Maximum Weight Clique Problem (MWCP). Although MWCP is NP-hard, its structure admits a principled greedy solution based on sample-wise marginal gains. Under a few mild conditions, we further prove that this unified objective enjoys a formal approximation guarantee, which applies to a broad family of importance metrics and provides practical design guidelines. Extensive experiments show that our method outperforms existing DP methods while substantially reducing training cost, reducing training time by over 40\% without sacrificing accuracy on ImageNet-1k with ResNet-50.

17.
arXiv (CS.LG) 2026-06-16

Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain

arXiv:2606.00558v2 Announce Type: replace Abstract: Transfer learning aims to facilitate the learning of a target domain by transferring knowledge from a source domain. The source domain typically contains semantically meaningful samples (*e.g.*, images) to facilitate effective knowledge transfer. However, a recent study observes that the noise domain constructed from simple distributions (*e.g.*, Gaussian distributions) can serve as a surrogate source domain in the semi-supervised setting, where only a small proportion of target samples are labeled while most remain unlabeled. Based on this surprising observation, we formulate a novel problem termed *Semi-Supervised Noise Adaptation* (SSNA), which aims to leverage a synthetic noise domain to improve the generalization of the target domain. To address this problem, we first establish a generalization bound characterizing the effect of the noise domain on generalization, based on which we propose a Noise Adaptation Framework (NAF). Extensive experiments demonstrate that NAF effectively leverages the noise domain to tighten the generalization bound of the target domain, leading to improved performance. The codes are available at https://github.com/AIResearch-Group/SSNA.

18.
arXiv (quant-ph) 2026-06-24

Revealing high-dimensional entanglement through symmetry

arXiv:2606.23817v1 Announce Type: new Abstract: Photons encoded in discrete time bins can be routinely prepared in temporal superposition states, enabling high-dimensional entanglement and enhanced quantum communication rates. However, characterizing this high-dimensional entanglement presents significant challenges, namely due to the involved measurement complexity or reliance on restrictive assumptions that compromise the generality of traditional approaches. Here, we develop and experimentally demonstrate a simple linear-optical scheme based on particle-exchange symmetry that allows us to probe high-dimensional entanglement in time-bin-encoded states. Combining Hong-Ou-Mandel interference with suitable transformations, our method not only certifies entanglement but also lower-bounds its dimensionality using only two dichotomic symmetry-based measurements. This bound is obtained through a new rigorous theoretical analysis and can be further improved by weak, physically motivated assumptions. The scheme remains effective at any timescale, even far below the temporal detector resolution used. Our work provides a powerful state-characterization tool and demonstrates that we can prove high-dimensional temporal entanglement on timescales inaccessible to the setup.

19.
arXiv (quant-ph) 2026-06-16

Against probability: A quantum state is more than a list of probability distributions

arXiv:2601.18872v2 Announce Type: replace Abstract: The state of a quantum system can be represented by listing the outcome probabilities for a tomographically complete set of measurements. Such representations appear throughout physics, for example, in quantum field theory via correlation functions and in quantum foundations within generalized probabilistic frameworks. In this paper, we show a no-go result: To enable useful statements, the probability representation must be topologically robust$\unicode{x2014}$preserving the notion of closeness between states. Yet, a topologically robust probability representation cannot simultaneously retain other essential structure, such as the subsystem structure.

20.
medRxiv (Medicine) 2026-06-15

Instrumental Activities of Daily Living in Older Adults with Epilepsy: A Cross-Sectional and Longitudinal Multicenter Study

Objective: Instrumental activities of daily living (IADLs) represent a critical but understudied measure of day-to-day function in persons with epilepsy(PWE). In the multicenter Brain Aging and Cognition in Epilepsy (BrACE) study of PWE aged greater than or equal to 55 years, we examined the proportion, clinical correlates, epilepsy-related predictors, and longitudinal trajectory of IADL impairment. Methods: IADLs were assessed using the Functional Activities Questionnaire (FAQ; range=0 to 30; higher=more impaired); a FAQ greater than or equal to 2 defines MCI-level impairment, and a FAQ greater than or equal to 5 defines dementia-level functional impairment. Multivariable logistic regression identified predictors of baseline function. Global cognition (Montreal Cognitive Assessment [MoCA]), individual cognitive measures, and quality of life (QOL) were compared between the impaired and unimpaired groups. Linear regression evaluated predictors of longitudinal functional decline. Results: Of 57 participants (mean age=66.6 years; female=52.6%), 38.6% (n=22) had MCI-level functional impairment and 17.5% (n=10) had dementia-level functional impairment. In univariate analyses, worse FAQ scores were associated with lower education, higher area deprivation index, early-onset epilepsy (EOE less than 60 years), antiseizure medication polytherapy, and epilepsy localization. In multivariable analysis, temporal lobe epilepsy (OR=4.46, 95% CI=1.09, 21.83,p=0.047), EOE(OR=7.14, 95% CI=1.16, 59.97, p=0.046), and lower education(OR=0.70,95% CI=0.49, 0.93, p=0.025) remained independently associated with baseline MCI-level functional-impairment. Lower education (OR=0.55,95% CI=0.29, 0.84, p=0.021) was the only factor associated with dementia-level IADL-impairment. IADL-impaired participants demonstrated lower verbal memory scores (adjusted p=0.041) and MoCA scores (adjusted p

21.
arXiv (CS.AI) 2026-06-24

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference

arXiv:2606.24467v1 Announce Type: new Abstract: Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs. These methods ignore the different functionalities of attention heads, leading to the eviction of critical tokens and thus degrading the performance of LLMs. To address this issue, we propose CompressKV, a resource-efficient KV-cache compression framework for GQA-based LLMs. Instead of aggregating attention scores from all heads, CompressKV identifies Semantic Retrieval Heads (SRHs) that capture both the initial and final tokens of a prompt and semantically important mid-context evidence, and uses them to select tokens whose KV pairs should be retained. Furthermore, CompressKV allocates cache budgets across layers according to offline estimates of layer-wise eviction error. Experiments on LongBench and Needle-in-a-Haystack show that CompressKV consistently outperforms existing KV-cache eviction methods across memory budgets. Notably, it preserves over 97\% of full-cache performance using only 3\% of the KV cache on LongBench question-answering tasks and achieves 90\% accuracy with just 0.7\% KV storage on Needle-in-a-Haystack. These results demonstrate an improved resource–performance trade-off for long-context LLM inference. Our code is publicly available at: https://github.com/TUDa-HWAI/CompressKV

22.
arXiv (CS.CL) 2026-06-16

A Large-Scale Multi-Dimensional Empirical Study of LLMs for Conversation Summarization

Despite the significant advancement of LLMs in conversation summarization, their evaluation remains limited by insufficient scenarios, input lengths, and sample sizes. Furthermore, existing benchmarks often omit frontier reasoning systems and efficient small models, or lack fine-grained, multi-dimensional assessments. To bridge these gaps, we propose OmniCSEval, a unified benchmark comprising 1,800 diverse conversations across six real-world scenarios, featuring context lengths ranging from 128 to 32k tokens. For fine-grained evaluation, we employ a bidirectional fact-checking framework that integrates key fact matching to assess completeness and conciseness, alongside summary fact verification to evaluate faithfulness. To ensure reliable assessment, we establish a human-LLM collaborative pipeline for key fact extraction and a multi-LLM consensus verifier for summary fact decomposition. Leveraging this framework, we evaluate 28 LLMs across four distinct categories grouped by reasoning capability and model scale. Our extensive empirical study reveals critical insights regarding the cross-scenario challenges current LLMs continue to face, the impacts of reasoning and scale, and the efficiency and adaptability of reasoning models. We also provide guidance for system selection in real-world deployments.

23.
arXiv (CS.CV) 2026-06-19

TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living

Long Video Question Answering (LVQA) requires identifying sparse, query-relevant evidence within hours-long untrimmed videos. Existing approaches either process videos densely with large vision-language models (VLMs), incurring prohibitive computational cost, or rely on sparse caption-based reasoning, which often misses temporally localized and motion-centric evidence. We introduce TimeProVe, a cost-efficient hybrid framework for temporally grounded reasoning in long videos. TimeProVe first employs lightweight modules to generate action-grounded answer–evidence hypotheses and subsequently invokes an expensive VLM only for targeted verification. The core of our framework lies in the Action-based Candidate Evidence (ACE) module, which converts temporally localized actions into query-conditioned candidate answers and supporting evidence windows through lightweight LLM reasoning. We further introduce OpenTSUBench (OTB), an open-ended benchmark designed to evaluate temporally grounded reasoning in real-world Activities of Daily Living (ADL) scenarios. Experiments show that TimeProVe outperforms the strongest baseline on OTB by 7.3%, while reducing VLM calls by 75% and inference cost by 93%. Furthermore, without explicit temporal grounding training, TimeProVe achieves competitive performance on Charades-STA, and reaches state-of-the-art results when enhanced with grounding VLMs.

24.
arXiv (CS.CV) 2026-06-18

Posterior Continuation with Noise-Conditioned Frequency Exposure for Diffusion Inverse Problems

Diffusion posterior sampling solves inverse problems by combining a pretrained diffusion prior with measurement-consistency guidance. However, full-band guidance can be unreliable at high noise levels, where clean estimates contain score-induced errors and high-frequency measurement directions are weakly identifiable. We argue that posterior guidance should expose measurement frequencies according to the instantaneous diffusion noise level. Based on this principle, we propose a posterior continuation framework that constructs a family of intermediate posteriors whose likelihood emphasizes currently reliable frequency bands and gradually returns to full-band consistency. We instantiate this framework with a stabilized sampler that combines a diffusion predictor, frequency-limited likelihood refinement, and a Haar-domain commitment rule that commits reliable coarse corrections while deferring weakly identifiable details. Across super-resolution, inpainting, and deblurring, our method achieves competitive-to-state-of-the-art restoration performance, including up to 5 dB PSNR improvement on motion deblurring over strong baselines in evaluations on FFHQ and ImageNet.

25.
arXiv (CS.CL) 2026-06-16

TokenPilot: Cache-Efficient Context Management for LLM Agents

As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize token footprints; however, their unconstrained sequence mutations alter layouts, introducing prefix mismatches and cache invalidation. This reveals a critical trade-off between text sparsity and prompt cache continuity. To address this, we present TokenPilot, a dual-granularity context management framework. Globally, Ingestion-Aware Compaction acts as a framework harness to stabilize prompt prefixes and eliminate open-world environmental noise at the ingestion gate. Locally, Lifecycle-Aware Eviction monitors the ongoing residual utility of context segments, enforcing a conservative batch-turn schedule to offload content segments only when task relevance expires. Experiments on PinchBench and Claw-Eval under both isolated and continuous modes demonstrate that TokenPilot reduces costs by 61% and 56% in isolated mode, and 61% and 87% in continuous mode, while maintaining competitive performance compared to prior systems. TokenPilot has been integrated into LightMem2 at https://github.com/zjunlp/LightMem2.