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.
arXiv (CS.AI) 2026-06-12

EpiBench: Verifiable Evaluation of AI Agents on Epigenomics Analysis

arXiv:2606.13602v1 Announce Type: new Abstract: We introduce EpiBench, a verifiable benchmark for short-horizon epigenomics analysis. EpiBench evaluates whether agents can make well-defined analysis decisions from realistic workflow states and return deterministically gradable answers. The benchmark includes 106 evaluations across CUT\&Tag/CUT\&RUN, ATAC-seq, ChIP-seq, and DNA methylation workflows. Across 5,088 valid trajectories from 16 model-harness pairs, no system passed a majority of attempts: GPT-5.5 / Pi led at 45.0\% (143/318 attempts; 95\% confidence interval (CI), 36.3–53.7), followed by GPT-5.5 / OpenAI Codex at 39.9\% (127/318 attempts; 95\% CI, 31.6–48.3). Claude Opus 4.8 Max / Pi and GPT-5.4 / Pi each passed 39.0\% (124/318 attempts; 95\% CI, 30.2–47.8 and 31.0–47.0, respectively). Performance varies across assay types, and many failed runs still contain parts of the correct answer. Agents often found the right files and computed useful intermediate results, but failed when the task required deeper, assay-specific scientific judgment.

02.
bioRxiv (Bioinfo) 2026-06-10

ECMME: an atlas of selection pressures on the mammalian extracellular matrix reveals contrasting evolutionary dynamics

The extracellular matrix (ECM) is a fundamental metazoan innovation that provides structural support and regulatory cues essential for multicellular life. While core matrisome components are subject to strong functional constraints, their evolutionary dynamics at the molecular level remain incompletely characterized. Here, we present a comprehensive per-residue analysis of selection pressures across 272 human core matrisome proteins using high-quality orthologous sequences from up to 228 placental mammal species. We developed an automated pipeline integrating ortholog identification, codon-aware alignments, and site-specific selection analyses with the MEME and FUBAR methods from the HyPhy suite. Results reveal pervasive strong purifying selection across the matrisome, consistent with its structural and functional indispensability. This is accompanied by episodic positive selection and rarer pervasive positive selection, with collagens exhibiting significantly elevated episodic positive selection compared to glycoproteins and proteoglycans. To facilitate community access, we developed ECMME (ECM Molecular Evolution) browser, an intuitive open-access web resource that visualizes selection metrics plotted directly onto protein topologies. ECMME allows researchers to seamlessly browse and investigate the data, providing a powerful framework for interpreting functional sites. It is available online and requires no local installation or set-up (https://izzilab-ecmme.share.connect.posit.cloud/).

03.
arXiv (math.PR) 2026-06-17

Persistence diagrams of random triangular matrices over finite fields

arXiv:2606.17895v1 Announce Type: cross Abstract: Let us consider a random infinite lower triangular matrix, where the entries on and below the diagonal are i.i.d. uniform random elements of a fixed finite field. We investigate the evolution of the span of the first $n$ rows of this matrix as $n$ grows. Many properties of this evolving subspace can be captured with the help of the verbose persistence diagram, which is a standard tool in stochastic topology and topological data analysis. We give an explicit formula for the distribution of the persistence diagram. We prove a law of large numbers for the distribution of lifetimes. We also describe the fluctuations of the persistent Betti numbers.

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

Learning to Hear Hesitation: Continual Learning for Disfluency-Aware ASR

Despite advances in large-scale Automatic Speech Recognition (ASR), disfluent speech remains challenging, as state-of-the-art systems are often optimized to omit disfluencies, leading to information loss and hallucinations. Prior work has focused on verbatim transcription and the integration of disfluency markers, but adapting models on limited datasets can lead to catastrophic forgetting of general-domain knowledge. We address this gap by leveraging continual learning (CL) with explicit disfluency tokens. We first introduce these tokens into a pretrained ASR model to establish stable token mechanisms, and then continue training on additional datasets with varying disfluency distributions. Through a detailed analysis of model dynamics during training, we identify a trade-off between marker learning and ASR performance, and a consistent cross-attention head mechanism shared across CL methods.

05.
arXiv (CS.LG) 2026-06-18

On Local Population-Risk Certificates

作者:

arXiv:2606.19147v1 Announce Type: cross Abstract: This paper develops local certificates for population-risk increments around a current model. For a local candidate set \(\mathcal D\), the certificate is a two-sided confidence band for \(P({\ell_{\theta+v}-\ell_\theta})\) over \(v\in\mathcal D\). As an application, the upper endpoint of this band yields a risk-controlled update rule: an update is accepted only when its certified upper endpoint is nonpositive; otherwise the current model is retained.

06.
medRxiv (Medicine) 2026-06-12

Does the method matter? Evaluating the effectiveness, efficiency and ease of hearing-aid gain self-adjustment

In conventional hearing-aid personalisation, clinicians cannot hear what their patients hear, and patients cannot often reliably detect or describe what they hear. Self-adjustment avoids this issue but requires user controls that adjust hearing-aid signal processing parameters to be effective, efficient and easy. In this study, we explored (a) the roles of interface complexity and stimulus type in the self-adjustment of hearing-aid gain, and (b) how well individuals can adjust one sound to match another to assess the same interfaces and stimuli. Adult hearing-aid users with mild to moderate symmetrical sensorineural hearing loss repeatedly adjusted the gain (a) to their preference from individual prescription (n = 41) and (b) to match their previous preferences from a random starting point (n = 32) using three interfaces representing different bass/mid/treble configurations and three stimuli (music, speech and speech-in-noise). The large interindividual variability in self-adjusted gains clustered into three patterns of deviation from initial prescription: increased relative bass, overall gain reduction, and close to initial prescription. There were no substantial effects of interface nor stimulus on self-adjustment reliability (median {sigma} = 2.8 dB), whereas absolute sound-matching error increased with increasing interface complexity and centre frequency. Neither individual matching accuracy nor questionnaire responses predicted either self-adjusted gains or reliability. Overall, these results show that many - but not all - hearing-aid users can adjust gains with reasonable reliability, and while it can be difficult to predict the behaviour from the individual, the individual applies a similar self-adjustment behaviour across different interfaces and stimuli.

07.
arXiv (quant-ph) 2026-06-15

All about quantum error correction: distillation, mitigation, self-correction and beyond

作者:

arXiv:2606.14034v1 Announce Type: new Abstract: In this work, it is shown that many quantum error-manipulating techniques, such as distillation, error mitigation, and dynamical decoupling, are special cases of the most general framework for quantum error correction. This unifying perspective is achieved by extending quantum error correction to include state-adaptive and channel-adaptive settings, as well as multi-stage coding scenarios. Based on this insight, a model of self-correcting quantum memory is also proposed. This work clarifies the relationship among these techniques and illustrates, through explicit constructions, how the unified perspective can guide the design of reliable quantum information systems.

08.
arXiv (CS.CL) 2026-06-19

Code-Switching Reveals Language Anchoring in Multilingual LLMs

Multilingual Large Language Models (MLLMs) are increasingly expected to handle Code-Switched (CS) inputs, yet mixing languages frequently degrades performance relative to source- or target-language monolingual counterparts. To understand this degradation, we use grammar-forced CS as a controlled diagnostic setting for locating CS representations relative to their source and target counterparts. We introduce Anchor Bias, a geometric measure that quantifies language anchoring, whether a CS hidden state aligns closer to its source or target language counterpart. Across diverse MLLMs, Anchor Bias reveals a consistent grammar-frame effect: source-framed CS stays source-anchored, whereas target-framed CS shifts target-ward and shows larger Question Answering (QA) degradation. Motivated by this representational pattern, we propose CANVAS (Contextual Anchor-based Neural Vector Alignment Steering), an inference-time intervention that extracts a source-side canvas from the input and softly steers target-language hidden states toward the source anchor during prefill. CANVAS consistently recovers QA F1 across MLLMs and CS conditions, showing that internal anchoring signals provide an actionable target for mitigating CS inference failures.

09.
arXiv (CS.CL) 2026-06-12

LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling

Search agent benchmarks exemplified by BrowseComp have rapidly saturated over the past year, with the strongest models surpassing 90% accuracy. Since these benchmarks are predominantly human-authored, annotators lack a global perspective on entity statistics and cannot systematically maximize search space size and structural complexity. This creates a difficulty ceiling that is hard to break. To address this, we introduce LoHoSearch (Long-Horizon Search Agents), a challenging benchmark comprising 544 human-verified questions across 11 domains. LoHoSearch is constructed via an automated pipeline built upon a knowledge graph covering over 7 million Wikipedia entities, which selects relations with large search spaces and assembles them into structurally complex questions with KG-verified unique answers. Our evaluation demonstrates that even the strongest model achieves only 34.74% accuracy, and existing context management strategies (best +6.8%) yield far smaller gains than on prior benchmarks. LoHoSearch provides a more demanding standard for evaluating long-horizon reasoning and context management in search agents.

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

Temporal Difference Learning for Diffusion Models

Diffusion models are typically trained with objectives that focus on local denoising targets at individual time steps (or adjacent pairs), which do not enforce consistency between predictions along the denoising trajectory. This lack of cross-time consistency can degrade performance, especially for few-step samplers. We introduce a temporal difference (TD) objective that penalizes inconsistency of the model's multi-step progress along the denoising path. By reformulating the diffusion process as a Markov reward process and casting denoising as a policy evaluation problem in reinforcement learning, we derive a unified TD approach that applies to both discrete- and continuous-time diffusion formulations. We further propose a principled sample-based reweighting method that stabilizes training. Empirically, we show that using our TD training can significantly improve sample quality measured by FID, with stronger advantages when the number of sampling steps is small, highlighting its practical utility under low-computation-budget scenarios. We provide ablation studies to justify our design choices, including pairwise loss reweighting, regularization weight, and one-step stride. Overall, our TD approach can be a general drop-in that enforces cross-time consistency and improves generation quality across different diffusion generative models.

11.
arXiv (CS.CL) 2026-06-11

Redesign Mixture-of-Experts Routers with Manifold Power Iteration

Router is the cornerstone component to the Mixture-of-Experts models. Serving as expert proxies, the rows of the router matrix compute their similarity to the MoE inputs to determine which subset of experts is activated. Ideally, each router row is designed to encode the expert matrix into this representative vector, such that its dot-product with token can better reflect token-expert affinity. However, there exists no design principles to enforce this condensation. In this paper, we propose to align each router row with the principal singular direction of the associated expert, as this direction provides the most expressive mathematical description of a matrix. Based on this principle, we propose a router redesign with Manifold Power Iteration (MPI). Specifically, it introduces a "Power-then-Retract" paradigm, where a power iteration step is performed on the router weights, followed by a retraction to impose a norm constraint to ensure both efficiency and stability. Theoretically, we show that MPI drives router rows to converge toward the principal singular directions of associated experts. Empirically, we pretrain MoE model across scales from 1B to 11B parameters to confirm that this alignment facilitates more effective MoE models.

12.
arXiv (CS.LG) 2026-06-11

Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation

arXiv:2606.11891v1 Announce Type: cross Abstract: Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy. A natural design choice is whether to use a single (unified) critic that estimates the combined value of all objectives, or separate (dual) critics with disjoint reward signals. We present a controlled comparison on the Unitree G1 humanoid (23 active DoF) in NVIDIA Isaac Lab, training loco-manipulation policies through a sequential curriculum spanning 13 levels from stationary reaching to walking with variable-orientation targets. In standardized evaluation, dual-critic policies reach targets 3.5$\times$ faster (6.5 vs. 22.6 simulation steps), achieve 2$\times$ higher throughput (14.3 vs. 7.0 validated reaches per 1,000 steps), and attain higher validated reach rates (65.2% vs. 53.8%) compared to the unified-critic policy. Notably, additional anti-gaming reward mechanisms provide no further improvement beyond the architectural change alone (60.9% vs. 65.2%). These results have direct implications for the emerging paradigm of RL fine-tuning of imitation-learned policies: when refining a pre-trained manipulation policy with RL, a unified critic risks suppressing the learned behavior through competing locomotion gradients. These findings demonstrate that critic architecture is a primary - and often overlooked - design choice in multi-objective humanoid RL, with greater impact than reward engineering on reaching efficiency.

13.
medRxiv (Medicine) 2026-06-16

Adverse Childhood Experiences and Growth Outcomes in Childhood: A Longitudinal EHR-Based Study

Question Are adverse childhood experiences (ACEs) associated with altered growth trajectories in childhood? Findings In this cohort study of 412,549 children and adolescents, ACEs were associated with lower height throughout childhood, earlier pubertal timing, and shorter final stature. Height differences emerged approximately 2 years before ACE documentation and were greatest among those with earlier documentation. Meaning These findings suggest that early adversity affects physical growth in children and may serve as a measurable indicator of the biological consequences of early-life stress, especially in those with documentation of ACEs prior to the onset of typical pubertal growth. Importance Adverse childhood experiences (ACEs) are among the strongest risk factors for long-term mental and physical health complications, yet their impact on physical growth in childhood remains incompletely understood. Objective To determine the association of ACEs on childhood growth trajectories and growth dynamics. Design, Setting and Participants Retrospective cohort study using longitudinal electronic health record data. Data was collected from participants between February 1999 and August 2025. A large academic medical center biobank linked to deidentified electronic health records in the southeastern United States. A total of 412,549 individuals with at least 2 recorded height measurements between the ages of 2 and 20 were included in the primary analysis. Growth curve analyses were performed in a subset of 199,844 individuals with at least 3 height measurements spanning at least 2 years. Genetic analyses were performed in a subset of 10,114 individuals of primarily European ancestry. Exposure(s) Documented exposure to adverse childhood experiences before age 18 years identified through a natural language processing algorithm. Main Outcome(s) and Measure(s) Height-for-age z-scores across childhood, final attained height, and growth curve parameters estimated using SuperImposition by Translation and Rotation (SITAR) modeling. Results Among 412,549 participants, 18,502 (4.5%) had clinically documented ACEs during childhood. ACE documentation was associated with lower height-for-age z-scores throughout childhood and adolescence. Final attained height was significantly lower among ACE-documented individuals, with mean differences of -3.0 cm among males (174.0 cm vs 177.0 cm, p < 0.001) and -1.3 cm among females (161.8 cm vs 163.1 cm, p < 0.001). Height differences emerged approximately 2 years before clinical ACE documentation. Earlier age at first ACE documentation was associated with progressively shorter final attained height, with each year decrease in age at ACE documentation associated with a decrease in final height of -0.20 cm in females and -0.35 cm in males. Those with first ACE documented prior to pubertal age also showed the most pronounced growth dynamic differences, with males demonstrating a mean reduction in size of 5.25 cm (95% CI, -6.79 cm to -3.70 cm) and 1.26-year earlier pubertal timing (95% CI, -1.50 to -1.03 years), and females demonstrating a reduction in growth curve size of 3.62 cm (95% CI, -4.83 to -2.41 cm) and 1.14-year earlier pubertal timing (95% CI, -1.29 to -0.99 years). Conclusions and Relevance In this large clinical cohort, clinically documented ACEs were associated with time-dependent reductions in stature, earlier pubertal timing, and short final attained height. These findings suggest that early childhood adversity may have lasting effects on physical development and highlight growth trajectories as a potential marker of the biological consequences of early-life stress.

14.
arXiv (CS.CL) 2026-06-12

Agentic MPC for Semantic Control System Resynthesis

While MPC effectively handles structured, diverse, and low-level specifications, it lacks the capability to dynamically incorporate high-level contextual information such as social norms, user intent, or natural language instructions. To address this limitation, this manuscript introduces an agentic MPC framework that enables context-aware, semantically adaptive control synthesis by integrating with large language model-based agents. The agent interprets heterogeneous inputs, including natural language messages, environmental observations, and external knowledge, to resynthesize the control specifications. The effectiveness of the framework is demonstrated in an autonomous driving scenario, where the system aligns with personal preferences or responds to social situations such as emergency vehicle yielding.

15.
arXiv (CS.LG) 2026-06-19

Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation

arXiv:2606.20118v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies have shown strong potential for general-purpose manipulation, yet they often fail on novel, out-of-distribution objects whose appearance or geometry deviates from the training distribution. The standard remedy is to collect multi-view teleoperation data for every failure case, but this scales poorly in both cost and time. We introduce Pose6DAug, a failure-driven data augmentation framework that turns a policy's own successful episodes into targeted demonstrations for its failure modes, without any new data collection. Our key insight is that each successful episode already encodes a physically valid action trajectory together with calibrated multi-view observations. By swapping only the manipulated object while preserving this trajectory, we obtain new and physically grounded demonstrations. However, naive 2D video editing breaks multi-view consistency and physical plausibility, particularly under heavy occlusion and egocentric viewpoints. Our method instead operates directly in 3D, anchoring the target object with an explicit mesh driven by a temporally coherent 6D pose trajectory, ensuring geometrically consistent renderings across all camera views. Fine-tuning a VLA on data augmented by our method improves success rates by 16.5% relative to the state-of-the-art baseline on novel objects, while preserving in-distribution performance. These results show that multi-view and physically consistent augmentation is a practical path to scalable VLA generalization.

16.
arXiv (CS.AI) 2026-06-18

RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents

arXiv:2606.19047v1 Announce Type: new Abstract: Multi-turn tool-use RL is bottlenecked by the rapid depletion of informative samples in static datasets. We observe that the gradient signal in GRPO concentrates on tasks with the highest rollout reward variance, a consequence of the Popoviciu upper bound. Consequently, samples near the agent's capability boundary – where successes and failures are roughly balanced – contribute disproportionately large policy gradients. As training progresses, this boundary continuously shifts, which gradually depletes the pool of informative samples in a static dataset. We propose RODS (Reward-driven Online Data Synthesis) to resolve this depletion. RODS closes the loop between RL training and data generation by repurposing the progress reward variance as a practical, zero-cost boundary detector that requires no extra inference beyond the rollouts already computed for training. It continuously identifies such boundary samples, synthesizes new multi-turn variants matching their structural complexity (e.g., API topology and dependency depth) via a skill-aligned resampling pipeline, and manages a dynamic replay buffer that co-evolves with the policy. Starting from 400 human seeds and maintaining an active training pool of ~800 samples, RODS achieves comparable performance to a 17K-sample offline pipeline while requiring roughly 20x fewer trajectories, and improves over fixed-data RL and environment augmentation in our controlled setting.

17.
arXiv (CS.CV) 2026-06-18

Semantic Robustness Certification for Vision-Language Models

Vision-language models (VLMs) are now widely used in downstream tasks. However, real-world applications often expose VLMs to distribution shifts induced by semantic variation (e.g., shape, size, and style). Robustness certification determines if a model's prediction changes when transformations are applied to its input. While most certification frameworks study geometric or pixel-level transformations over inputs, this work proposes a novel framework that enables certifying VLM robustness under semantic-level transformations. Leveraging the open-vocabulary capability of VLMs, we use text prompts as semantic proxies to construct transformations parameterized by an extent that controls the degree of semantic variation. By characterizing the VLM decision boundary in closed form, our framework quantitatively certifies extent intervals for which the predicted class remains unchanged under the semantic transformation. Our framework is the first to certify VLM robustness under semantic-level variations without requiring additional data for each variation, making it practical to apply. Experiments on both synthetic and real-world data show that our framework enables certifying robustness under diverse semantic variations across scenarios.

18.
arXiv (CS.AI) 2026-06-12

Creating and Evaluating K-12 GenAI Assessment Graders Through Context Engineering

arXiv:2606.12422v1 Announce Type: cross Abstract: The integration of large language models (LLMs) into educational assessment represents a transformative shift in classroom grading practices. While automated scoring systems and machine learning techniques have existed for decades, generative AI (GenAI) now enables educators to implement standards-based grading (SBG) with unprecedented efficiency and scale. This paper examines the theoretical foundations and evaluates an LLM grader that uses commercially available foundation models with context and prompt engineering to score student work against a rubric. Drawing on an empirical interrater agreement study using Massachusetts Comprehensive Assessment System (MCAS) data, we observed the Quadratic Weighted Kappa (QWK) and Proportional Reduction in Mean-Squared Error (PRMSE) across mathematics, science, and ELA, using Claude Sonnet 4, Haiku 4.5, GPT-5, and GPT-5 Mini. The results demonstrate that LLM graders, especially when based on foundational models with more parameters, achieve substantial agreement with human raters in mathematics and science assessments, while the performances vary in ELA, suggesting generic foundation models can be effective at scoring in given contexts. Additional analysis of teacher and student feedback reveals strong acceptance of AI-generated narrative feedback but skepticism toward numerical scores, suggesting that LLMs function most effectively as formative tools rather than summative evaluators. Our findings indicate that thoughtfully designed hybrid models that combine AI efficiency with teacher judgment can reduce workload, enhance feedback quality, and support equitable assessment practices without displacing professional expertise.

19.
arXiv (CS.LG) 2026-06-17

CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering

arXiv:2602.03420v2 Announce Type: replace-cross Abstract: Emotional expression in human speech is nuanced and compositional, often involving multiple, sometimes conflicting, affective cues that may diverge from linguistic content. In contrast, most expressive text-to-speech systems enforce a single utterance-level emotion, collapsing affective diversity and suppressing mixed or text-emotion-misaligned expression. While activation steering via latent direction vectors offers a promising solution, it remains unclear whether emotion representations are linearly steerable in TTS, where steering should be applied within hybrid TTS architectures, and how such complex emotion behaviors should be evaluated. This paper presents the first systematic analysis of activation steering for emotional control in hybrid TTS models, introducing a quantitative, controllable steering framework, and multi-rater evaluation protocols that enable composable mixed-emotion synthesis and reliable text-emotion mismatch synthesis. Our results demonstrate, for the first time, that emotional prosody and expressive variability are primarily synthesized by the TTS language module instead of the flow-matching module, and also provide a lightweight steering approach for generating natural, human-like emotional speech.

20.
arXiv (CS.LG) 2026-06-12

Multi-Token Residual Prediction

arXiv:2605.18817v2 Announce Type: replace Abstract: Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality compared to autoregressive models. In current practice, the number of tokens decoded per step is controlled by a confidence threshold, and quality degrades monotonically as more tokens are denoised per step. We introduce Multi-token Residual Prediction (MRP), a lightweight module that enables dependency-aware multi-token denoising within a single backbone forward pass. MRP exploits a key property of the denoising process: the logit distributions at adjacent denoising steps are remarkably similar. Rather than running the backbone a second time to obtain the next-step logits, MRP predicts the residual between steps from the backbone's hidden states, effectively denoising more tokens per backbone forward at a fraction of the cost. We apply MRP across the two operating regimes of DLM decoding. In the high-quality-low-throughput static denoising regime, MRP serves as a drafter for speculative decoding: its proposals are verified against the backbone, yielding lossless acceleration of up to 1.4x in SGLang. In the low-quality-high-throughput dynamic denoising regime, MRP instead drives a remasking scheme that revokes over-eager reveals, recovering most of the accuracy lost to aggressive low-threshold decoding and improving accuracy by up to 22.6 points on code generation task HumanEval and 17.7 points on reasoning task GSM8K.

21.
arXiv (CS.CL) 2026-06-19

Closing the Calibration Gap in Semantic Caching

Semantic caching cuts LLM inference costs by serving a cached response to semantically similar queries. Standard practice evaluates these systems using PR-AUC, a metric that only measures how well scores rank and ignores whether they are usable at a fixed threshold. We show this mismatch leads to systematically poor deployment choices, as models with the highest PR-AUC are often the worst in operation. We introduce Precision-Cache Hit Ratio (P-CHR) AUC, a cache-aware metric that measures precision across cache utilization levels, and Calibration Retention Rate (CRR), which captures how much offline ranking quality survives at deployment. We decompose the operational gap between offline and deployed quality into a recoverable calibration component and an irreducible structural component fixed by the dataset's positive rate. Our experiments show that the calibration gap is governed by the training objective rather than data scale, and post-hoc calibration only partially closes it. Ultimately, model selection for semantic caching is a calibration problem, not a ranking one, and measuring it is the first step to closing the gap.

22.
arXiv (CS.CL) 2026-06-11

FOCUS: DLLMs Know How to Tame Their Compute Bound

Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding cost. In this work, we identify a key inefficiency in DLLM decoding: while computation is parallelized over token blocks, only a small subset of tokens is decodable at each diffusion step, causing most compute to be wasted on non-decodable tokens. We further observe a strong correlation between attention-derived token importance and token-wise decoding probability. Based on this insight, we propose FOCUS, an inference system designed for DLLMs. By dynamically focusing computation on decodable tokens and evicting non-decodable ones on-the-fly, FOCUS increases the effective batch size, alleviating compute limitations and enabling scalable throughput. Empirical evaluations demonstrate that FOCUS achieves up to 3.52$\times$ throughput improvement over the production-grade engine LMDeploy in large-batch settings, while preserving or improving generation quality across multiple benchmarks.

23.
arXiv (CS.LG) 2026-06-15

AGORA: Can Deliberation and Governance Gates Absorb Participation Bias in Transit Planning?

arXiv:2606.13696v1 Announce Type: cross Abstract: Transit network design depends not only on the optimization algorithm but also on who shows up to the public hearing. Current practice often collects one-directional comments from self-selected attendees, leaving participant mix as an uncontrolled source of outcome variation. We present AGORA, a framework that holds the network, demand, and solver fixed while systematically varying meeting composition through stakeholder agents, structured deliberation, and governance gates. Across two standard benchmark networks at different scales, we find that (i) aggregate outcomes vary little across compositions, but on tail risk and fairness disparity, representative sampling still tends to outperform skewed compositions; (ii) without deliberation, composition produces no variation at all, showing that deliberation is the mechanism through which who attends affects outcomes; and (iii) governance gates compress cross-profile variance without shifting the average outcome on Mandl, but low acceptance on Mumford0 shows thresholds require instance-specific calibration. These findings reframe participation bias from an uncontrollable input to a process-design problem: even without guaranteed representative attendance, well-structured deliberation and governance criteria can substantially reduce how much outcomes depend on who is in the room.

24.
arXiv (CS.CL) 2026-06-12

ChiKhaPo: A Large-Scale Multilingual Benchmark for Evaluating Lexical Comprehension and Generation in Large Language Models

Existing benchmarks for large language models (LLMs) are largely restricted to high- or mid-resource languages, and often evaluate performance on higher-order tasks in reasoning and generation. However, plenty of evidence points to the fact that LLMs lack basic linguistic competence in the vast majority of the world's 3800+ written languages. We introduce ChiKhaPo, consisting of 8 subtasks of varying difficulty designed to evaluate the lexical comprehension and generation abilities of generative models. ChiKhaPo draws on existing lexicons, monolingual data, and bitext, and provides coverage for 2700+ languages for 2 subtasks, surpassing any existing benchmark in terms of language coverage. We further show that 6 SOTA models struggle on our benchmark, and discuss the factors contributing to performance scores, including language family, language resourcedness, task, and comprehension versus generation directions. With ChiKhaPo, we hope to enable and encourage the massively multilingual benchmarking of LLMs.

25.
arXiv (CS.CV) 2026-06-17

NeuroClaw Technical Report

Agentic artificial intelligence systems promise to accelerate scientific workflows, but neuroimaging poses unique challenges: heterogeneous modalities (sMRI, fMRI, dMRI, EEG), long multi-stage pipelines, and persistent reproducibility risks. To address this gap, we present NeuroClaw, a domain-specialized multi-agent research assistant for executable and reproducible neuroimaging research. NeuroClaw operates directly on raw neuroimaging data across formats and modalities, grounding decisions in dataset semantics and BIDS metadata so users need not prepare curated inputs or bespoke model code. The platform combines harness engineering with end-to-end environment management, including pinned Python environments, Docker support, automated installers for common neuroimaging tools, and GPU configuration. In practice, this layer emphasizes checkpointing, post-execution verification, structured audit traces, and controlled runtime setup, making toolchains more transparent while improving reproducibility and auditability. A three-tier skill/agent hierarchy separates user-facing interaction, high-level orchestration, and low-level tool skills to decompose complex workflows into safe, reusable units. Alongside the NeuroClaw framework, we introduce NeuroBench, a system-level benchmark for executability, artifact validity, and reproducibility readiness. Across multiple multimodal LLMs, NeuroClaw-enabled runs yield consistent and substantial score improvements compared with direct agent invocation. Project homepage: https://cuhk-aim-group.github.io/NeuroClaw/index.html