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.CL) 2026-06-15

Spatio-Temporal Audio Language Modeling for Dynamic Sound Sources

Sound events are entities with semantic identities, locations, and trajectories, but current audio-language models usually reason about clips as global event content. Conversely, sound event localization models track source directions over time but offer limited semantic coverage for language reasoning. To address this gap, we introduce ST-AudioQA, a spatio-temporal audio QA dataset and benchmark built from first-order ambisonic (FOA) renderings of static and moving sound sources. Each scene provides source identity, activity, direction, distance, and motion metadata, enabling dense trajectory supervision and questions about what is sounding, where it is, how it moves, and how sources relate. We further propose ST-Audio Encoder, a time-resolved FOA audio encoder that learns event semantics together with source trajectories, and ST-AudioLM, which connects the audio tokens from the encoder to an LLM for spatio-temporal audio QA. Experiments show that this representation improves the semantic-localization tradeoff and yields stronger reasoning performance than static spatial and localization-oriented baselines.

02.
arXiv (CS.AI) 2026-06-17

First, do NOHARM: towards clinically safe large language models

arXiv:2512.01241v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized. We present NOHARM (Numerous Options Harm Assessment for Risk in Medicine), a 1,100-task benchmark of primary care-to-specialist consultation cases to measure the frequency and severity of harm from LLM-generated medical recommendations. NOHARM covers 10 specialties, with 12,747 expert annotations for 4,249 clinical management options. Across 28 LLMs, recommendations carried the potential for severe harm in up to 22.6% of cases, with errors of omission accounting for more than 80% of severe errors. In a randomized trial of 101 generalist physicians, human benchmark performance significantly improved with AI assistance, yet physicians remained far from realizing the potential of AI tools, frequently ignoring essential advice surfaced by AI. Safety performance tracked general-intelligence and medical-knowledge benchmarks across the full range of models but decoupled at the frontier. Despite strong performance on existing evaluations, widely used AI models can produce medical advice with the potential for severe harm at non-trivial rates, highlighting the importance of explicit measurement of clinical safety.

03.
arXiv (CS.AI) 2026-06-11

A Five-Plane Reference Architecture for Runtime Governance of Production AI Agents

作者:

arXiv:2606.12320v1 Announce Type: new Abstract: Enterprise security was built to govern data boundaries: the protected surface was data at rest and in transit, and the controls – access control, data-loss prevention, perimeter inspection – governed crossings of that boundary. Production AI agents dissolve this assumption. An agent reads context, calls tools, invokes connectors, and modifies systems of record on an enterprise's behalf, so risk moves inside the workflow, into sequences of individually-permitted actions that may transform a business process no one authorized. Existing policy engines do not extend to this regime: they evaluate request-time decisions against atomic principals, where agentic systems require stateful evaluation against composite principals whose authority attenuates through delegation chains. We present a reference architecture for the runtime governance of production agents, built from four composable primitives: a five-plane decomposition (a reasoning plane that adjudicates intent, and four enforcement planes – network, identity, endpoint, data – that realize the decision), stop-anywhere mediation, composite principals with capability attenuation, and audit as a structured evidence substrate. We define a taxonomy of six interruption primitives that generalize allow and deny, state and argue for four correctness invariants, and demonstrate the foreclosure of seven production-agent threats across five concrete workflows. A reference implementation of the policy-engine core supplies measured evidence: attenuation correctness and evidence reconstructability hold on every trial, adjudication runs in single-digit microseconds, and the audit substrate's tamper-evidence behaves exactly as designed. We are explicit about scope: the architecture governs delegated action, not model behavior, and a full-system evaluation against a live agent benchmark is the invited next step.

04.
arXiv (CS.CV) 2026-06-18

DART: A design-aware microfluidic chip paradigm for real-time live-cell image analysis

High-throughput microfluidic live-cell imaging generates rich single-cell data. Yet semi-automated procedures for locating regions of interest (RoIs), each containing one cell population, and removing surrounding microfluidic structures from recorded images, scale with the number of RoIs. This prevents real-time image analysis and delays time-to-insight by hours to days. We introduce the Design-Aware and Real-Time capable (DART) paradigm for microfluidic cultivation chips, which aligns the CAD blueprint with the physical chip and thereby enables throughput-independent localization of all RoIs and fully automated image processing across diverse RoI geometries and chip layouts. DART establishes this alignment through embedded fiducial markers and deep-learning-based marker detection. We validate DART using the Swiss Army Knife chip, which combines eight structurally distinct RoI designs across 1164 RoI locations. DART localizes all RoIs in five minutes, removes microfluidic structures from raw microscopy images in 40 ms, and performs fully automated image analysis, including cell segmentation, in under 1.1 s per image. Together, these capabilities establish DART as an end-to-end hardware-software paradigm with real-time-capable analysis that paves the way toward closed-loop and outcome-driven smart microscopy.

05.
Nature Medicine 2026-06-15

Activity-dependent adaptive deep brain stimulation improves gait in Parkinson’s disease

Parkinson’s disease leads to a spectrum of locomotor deficits that vary in severity with the nature of daily activities and the fluctuating physiology of patients. Many of these deficits remain inadequately addressed by existing deep brain stimulation therapies that rely on activity-agnostic parameters optimized for cardinal motor symptoms. By contrast, therapies embedding activity-specific parameters have the potential to better address the entire range of symptoms. Here we expose physiological principles that enable real-time decoding of ongoing locomotor activities across motor fluctuations from the neural dynamics of the subthalamic nucleus. This decoding steered activity-dependent adaptations of deep brain stimulation therapies that improved locomotor deficits while preserving efficacy for cardinal motor symptoms across activities of daily living. Our activity-dependent framework provides a blueprint for next-generation neuromodulation therapies that continuously select parameters optimized to the behavioral context and fluctuating physiology of each patient. ClinicalTrials.gov registration NCT06791902 . Neural decoding algorithms that leverage physiological principles of locomotor encoding support activity-dependent deep brain stimulation therapies that improve locomotor deficits in people with Parkinson’s disease.

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

Focus When Necessary: Adaptive Routing and Collaborative Grounding for Training-Free Visual Grounding

While Multimodal Large Language Models (MLLMs) excel in cross-modal reasoning, they often struggle to perceive fine-grained details in complex high-resolution images. Recent training-free methods address this through image scaling and localized cropping. However, applying these manipulations indiscriminately introduces computational redundancy for simple queries and can degrade accuracy by truncating essential global context or introducing irrelevant background noise. To this end, we propose LazyMCoT, a dynamic and training-free framework that adaptively allocates visual grounding efforts based on sample difficulty. The framework features an Adaptive Routing mechanism that evaluates predictive uncertainty using first-token statistics from a single forward pass. This efficiently bypasses confident cases while ensuring the recall of difficult samples via conformal calibration. For these challenging cases, a Collaborative Grounding module integrates the inherent cross-modal attention of the model with an external visual expert through a two-stage refinement process. This refinement process generates a precise localized display to recover small or occluded targets. Extensive experiments across diverse benchmarks demonstrate that LazyMCoT rivals training-based approaches by simultaneously improving reasoning accuracy and reducing average inference latency. Our code is availble at https://github.com/TencentBAC/LazyMCoT.

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

The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation

LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized. We study repeated identical evaluations on 29 tasks spanning 10 categories using two OpenAI judge models (GPT-4o-mini and GPT-4.1-mini), with 50 pairwise trials and 50 pointwise trials per question, supplemented by temperature and prompt-sensitivity ablations. Across judges, pairwise preferences flip on average 13.6% of the time, with 28% of questions exceeding a 20% flip rate and one question reaching 56%. GPT-4o-mini also exhibits a significant first-position bias (72% A-majority, p = 0.024). At the same time, mean pointwise score gaps are small (0.19–0.36 on a 10-point scale) and not statistically significant in aggregate, producing a pairwise–pointwise gap: judges frequently choose a winner even when their own scalar scores provide little evidence of a meaningful quality difference. Beyond within-judge instability, cross-judge agreement is only 76% ($\kappa = 0.51$), semantically equivalent prompt templates change majority outcomes in 25% of tested cases, and deterministic decoding reduces but does not eliminate inconsistency. A reliability curve analysis shows that, in our dataset, 11 repeated trials are needed for a majority vote to recover the 50-trial reference verdict with 95% probability on average, rising to 15 for high-variance questions. These findings suggest that single-trial LLM judging is often too noisy for high-stakes evaluation, and that multi-trial aggregation, position randomization, and explicit uncertainty reporting should be standard practice. Because both judges are from a single provider, cross-provider replication remains an important next step.

08.
arXiv (CS.CL) 2026-06-16

How Far Can Machine Translation Quality Take You? Extrinsic Discourse Evaluation in Goal-Oriented Setups

Existing machine translation (MT) metrics and discourse-focused evaluations primarily assess translation quality intrinsically, without measuring the downstream consequences of translation errors. In this work, we focus on extrinsic discourse evaluation of machine translation under two distinct regimes: static and interactive. Under the static regime, we propose an entity counting task as a probe of referential consistency in discourse. We show that high intrinsic MT quality does not reliably predict downstream discourse success and strong MT systems still produce referential inconsistencies. For the interactive regime, we study the goal-oriented multi-agent Welfare Diplomacy game as a probe of long-horizon communication and coordination. We find that interaction-specific translation failures impact downstream coordination. Our results highlight goal-oriented environments as a viable framework for discourse-sensitive extrinsic MT evaluation.

09.
arXiv (CS.CV) 2026-06-18

iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance

Video Virtual Try-On (VVT) aims to seamlessly replace a garment on a person in a video with a new one. While existing methods have made significant strides in maintaining temporal consistency, they are predominantly confined to non-interactive scenarios where models merely showcase garments. This limitation overlooks a crucial aspect of real-world apparel presentation: active human-garment interaction. To bridge this gap, we introduce and formalize a new challenging task: Interactive Video Virtual Try-On (Interactive VVT), where subjects in the video actively engage with their clothing. This task introduces unique challenges beyond simple texture preservation, including: (1) resolving the semantic ambiguity of interactions from standard pose information, and (2) learning complex garment deformations from video where interactive moments are sparse and brief. To address these challenges, we propose iTryOn, a novel framework built upon a large-scale video diffusion Transformer. iTryOn pioneers a multi-level interaction injection mechanism to guide the generation of complex dynamics. At the spatial level, we introduce a garment-agnostic 3D hand prior to provide fine-grained guidance for precise hand-garment contact, effectively resolving spatial ambiguity. At the semantic level, iTryOn leverages global captions for overall context and time-stamped action captions for localized interactions, synchronized via our novel Action-aware Rotational Position Embedding (A-RoPE). Extensive experiments demonstrate that iTryOn not only achieves state-of-the-art performance on traditional VVT benchmarks but also establishes a commanding lead in the new interactive setting, marking a significant step towards more dynamic and controllable virtual try-on experiences.

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

From Affect Prediction to Affect Forecasting: Evidence for Distinct Information Sources in Longitudinal Text

Modeling dimensional affect in longitudinal text requires distinguishing current affect estimation from future affective change forecasting. Existing approaches often treat each text as an independent observation and apply similar assumptions to both tasks, without testing whether they rely on different information sources. This paper investigates that distinction using longitudinal self-reported ecological essays and feeling-word entries. We propose the Trait–State Affective Prediction (TSAP) framework and its temporal extension E-TSAP for per-text valence and arousal prediction, evaluated on a held-out prediction test set of 1,737 entries from 91 users. We further propose the Affective Change Forecaster Hybrid (ACF-Hybrid) for next-step affective change forecasting, evaluated on a held-out forecasting test set of 46 users. For prediction, E-TSAP achieves composite Pearson correlations of 0.670 for valence and 0.449 for arousal. For forecasting, textual representations perform worse than compact numeric trajectory baselines: the text-inclusive model achieves only r=0.316 for valence and r=0.284 for arousal, whereas a simple prior-state baseline reaches r=0.615 and r=0.670, respectively. ACF-Hybrid, using dimension-specific numeric trajectory features, achieves r=0.659 for valence and $r=0.658$ for arousal. These results show that textual semantics support current affect prediction, whereas future affective change is better captured through prior numeric trajectory dynamics.

11.
arXiv (CS.CV) 2026-06-15

Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings

Hallucinations in Large Vision-Language Models (LVLMs) remain a persistent challenge, often stemming from inadequate integration of visual information during multimodal reasoning. A key cause is the model's over-reliance on textual priors and underutilization of visual cues, leading to outputs that are linguistically fluent but visually inaccurate. For example, given an image of an empty kitchen countertop, an LVLM might hallucinate a "bowl of fruit" or "cup of coffee", relying on language associations rather than visual evidence. Most LVLMs incorporate visual features by appending them to the input stream of a pre-trained LLM and training on large-scale vision-language datasets. Our systematic analysis reveals that this strategy often leads to over-dependence on textual information due to the inherent bias of LLMs towards language-dominant representations. This imbalance skews attention towards the text over visual content, weakening the model's ability to ground outputs in visual inputs. To address this, we propose a simple yet effective visual feature incorporation method that encourages the model to learn visually-informed textual embeddings distinct from those of the base LLM and promotes a more balanced attention distribution. Experimental results across multiple hallucination benchmarks demonstrate that our method significantly reduces hallucinations and fosters more balanced multimodal reasoning. Notably, our approach achieves substantial gains, including +9.33% on MMVP-MLLM, +2.99% on POPE-AOKVQA, up to +3.4% on Merlin, and +3% on the hard-data split of HallusionBench.

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

Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems

arXiv:2606.18310v1 Announce Type: cross Abstract: Injecting malicious knowledge into retrieval-augmented generation (RAG) systems can manipulate retrieved evidence and mislead downstream generation, posing a serious security threat for AI applications. Existing RAG injection attacks mainly rely on manipulating external knowledge bases, such as crafting malicious corpus. However, the synthetic text crafted by such data-centric methods could be detectable, leading to the failure of attacks. Beyond corpus manipulation, open-source retrievers are increasingly exposing RAG systems to model-centric attacks. In this paper, we propose conflict-aware retriever editing, i.e., CAREATTACK, a model-centric retriever attack framework for malicious knowledge injection in RAG. Specifically, CAREATTACK consists two stages of conflict-aware retriever editing and attack-preserving anchor repair. Conflict-aware retriever editing adapts efficient closed-form parameter editing to the dense retrieval model, promoting malicious knowledge above benign competing passages and resolving potential parameter conflicts through graph-based conflict detection and parameter editing projection. Then, attack-preserving anchor repair performs lightweight calibration on the edited retriever to further eliminate the impact on non-target prompts while preserving the attack effectiveness for target prompts. We instantiate CAREATTACK on Qwen3-Embedding-0.6B and BGE-M3, and conduct evaluation on three benchmark datasets. Experimental results demonstrate our method substantially promote malicious passages into the retrieved knowledge of RAG systems and can perform attacks for batches of target prompts and passages, given the access of retrieval model parameters. Since most RAG systems are built upon open-source retrieval models, this work reveals a practical attack surface in RAG systems. Codes are public accessible at https://anonymous.4open.science/r/CareAttack-3F1C.

13.
medRxiv (Medicine) 2026-06-15

Midwifery Practice in Conflict Contexts: Lived Experiences from Somalia and Nigeria

Background: Midwives are a central cadre in the health system, particularly in conflict-affected settings where they are sometimes the primary or even only skilled providers available. Yet, despite their critical role, there is limited qualitative evidence capturing their lived experiences and how these shape workforce entry, retention, and overall well-being. Methods: Drawing on a phenomenological research methodology, this qualitative study was embedded within a larger prospective longitudinal cohort of midwifery students and graduates in Somalia and Nigeria. We conducted focus group discussions with graduate midwives (n=48 in Nigeria; n=63 in Somalia) to explore their experiences transitioning into the workforce and their realities working in health systems impacted by conflict and violent insecurity. Data were analysed using inductive thematic analysis. Results: Five themes emerged from the data: (1) job search and workforce entry, which was described as fraught with challenges and shaped by a set of formal systems in Nigeria but informal networks and structural barriers in Somalia (2) working conditions that were marked by resource scarcity, infrastructural challenges, and heavy and unreasonable workloads, (3) safety, security and coping strategies that differed across the two contexts but reflected persistent exposure to violence and a reliance on ad hoc and personal coping in lieu of systematic protection, (4) community perceptions of midwives, shaped and constrained by social and gender norms and (5) mental health and emotional wellbeing, highlighting stress, burnout and moral injury experienced by this cadre. Conclusion: Our findings highlight the profound challenges faced by midwives working in conflict-affected settings, and they shine a light on the urgent need to support and invest in this critical and predominantly female health workforce.

14.
arXiv (CS.CL) 2026-06-11

AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable

The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may reduce methodological diversity, or that they may amplify the analytic flexibility through which researchers reach motivated conclusions. We argue these worries target two empirically separable layers: a design layer of methodological choices, and a verdict layer in which a decision rule maps estimates to a substantive claim. We test both by running 20 independent executions of Claude Code and Codex on a prominent immigration and social-policy against a many-analysts human baseline. At the design layer, Codex matches human methodological diversity and Claude Code produces nearly three times as many specifications; both agents' effect estimates remain broadly aligned with the human consensus, and no agent model exactly matches any human model. A prompt-induced anti-immigration researcher prior reorganizes each agent's methodological decisions but, unlike for biased human analysts in the same data, does not shift aggregate estimates or final verdicts; nor do agents reroute along the methodological axes humans use to bias their estimates. At the verdict layer, an explicit confirmatory prompt flips Claude Code's verdicts from 10% to 90% support while leaving its coefficient distribution essentially unchanged, operating through rule omission rather than rule softening. AI agents can rival or exceed human methodological diversity at the design layer while remaining vulnerable at the verdict layer. In our setting, the locus of AI bias is not estimation but interpretation.

15.
arXiv (CS.CL) 2026-06-18

Possible or Definite? A Benchmark for Evaluating Diagnostic Uncertainty Preservation in Clinical Text

Large language models (LLMs) are increasingly used for clinical text tasks such as summarization and revision. While most studies evaluate the fluency and coherence of LLM-generated text, whether LLMs correctly preserve diagnostic uncertainty remains underexplored. In clinical practice, phrases such as ``possible pneumonia'' communicate the strength of available evidence and directly guide decisions about follow-up testing and treatment. Altering these uncertainty expressions can change the clinical meaning entirely. In this paper, we systematically evaluated this problem in two steps. First, we constructed a benchmark of 1,200 clinical documents with 9,184 uncertainty annotations across five levels. Second, we evaluated three LLMs on this benchmark. Our results show that (1) LLMs preserve the original uncertainty cues poorly, often less than half the time; (2) LLMs struggle with nuanced distinctions between adjacent levels. This work reveals a failure mode not captured by standard evaluation metrics and provides implications for the safe deployment of LLMs in clinical workflows.

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

SMART: A Flexible, Interpretable, and Scalable Spatio-temporal Brain Atlas from High-Resolution Imaging Data

We introduce SMART, a framework for learning a flexible, interpretable, and scalable spatio-temporal brain atlas from longitudinal high-resolution 3D medical images. Existing approaches to spatio-temporal atlas construction rely on black-box generative models that lack flexibility, limit interpretability, and struggle to scale to high-dimensional data. SMART addresses these challenges by learning a continuous disease-time atlas that decouples global group-wise disease dynamics from their patient-specific anatomical manifestation. Guided by anatomically inspired priors, SMART models interpretable global trajectories of regional progression along a shared disease timeline through region-specific differential equations. Global trajectories are further personalized to individual anatomies via dense diffeomorphic displacements parameterized by a flexible and scalable multi-scale Neural Cellular Automata. Evaluated on five longitudinal MRI datasets in Alzheimer's disease (ADNI-1/GO/2, OASIS-3, AIBL; > 1,300 subjects), SMART produces anatomically meaningful predictions of disease progression and achieves state-of-the-art forecasting accuracy and improved temporal consistency over adversarial and diffusion baselines. Our approach establishes a new paradigm for flexible, interpretable, and scalable modeling of spatio-temporal change in high-dimensional medical image time-series.

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

World Engine: Towards the Era of Post-Training for Autonomous Driving

Autonomous vehicles must operate safely in the real world, where errors can have severe consequences. Although modern end-to-end driving policies excel in routine scenarios, their reliability is limited by the scarcity of safety-critical ``long-tail'' events in real driving datasets. These rare interactions define the practical safety boundary of the learned policy, yet they are difficult to collect at scale in the real world. Here we show that this fundamental limitation can be addressed by post-training pre-trained driving models on synthesized high-stakes interactions. We introduce World Engine, a generative framework that reconstructs high-fidelity interactive environments from real-world logs and systematically extrapolates them into realistic safety-critical variations. This paradigm enables reinforcement-based post-training to align policies with safety constraints, circumventing the physical risks inherent in real-world exploration. On a public benchmark built on nuPlan, World Engine substantially reduces failures in rare safety-critical scenarios and yields significantly larger gains than scaling pre-training data alone. Furthermore, when deployed on a production-scale autonomous driving system, the resulting policy reduces simulated collisions and demonstrates measurable improvements in on-road testing, showing that post-training on synthesized, safety-critical interactions offers a scalable and effective pathway to safer autonomous driving. The full codebase suite, including training, is released to the public.

18.
arXiv (CS.LG) 2026-06-15

Learning Variable-Length Tokenization for Generative Recommendation

arXiv:2605.17779v2 Announce Type: replace Abstract: Generative recommendation reformulates recommendation as next-token prediction over discrete semantic identifiers (IDs). A fundamental yet unexplored design choice is that existing methods employ fixed-length tokenization for all items, implicitly assuming uniform encoding capacity regardless of item characteristics. Through systematic experiments across four datasets, we discover the Popularity-Length Paradox: popular items achieve optimal performance with short IDs, while tail items require substantially longer codes to capture discriminative semantics. This reveals a critical mismatch where popular items benefit from abundant collaborative signals and require minimal semantic detail, whereas tail items must rely on fine-grained content features due to sparse interaction data. To address this, we propose VarLenRec, a framework for learning variable-length tokenization. We develop Popularity-Weighted Information Budget Allocation (PIBA), an information-theoretic framework proving that optimal ID length should scale as a negative power of popularity. Directly implementing variable-length allocation faces two technical challenges: standard Euclidean residual quantization lacks geometric capacity to support diverse code lengths without distortion, and discrete length decisions are non-differentiable. We address these through Hyperbolic Residual Quantization, which leverages the exponential volume growth of the Poincaré ball to naturally stratify encoding capacity, and a Soft Length Controller, which enables differentiable length prediction via continuous layer retention probabilities regularized by PIBA-derived priors. Extensive experiments demonstrate that VarLenRec achieves significant improvements over state-of-the-art methods in recommendation accuracy and training/inference efficiency, revealing the importance of adaptive encoding capacity in generative recommendation.

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

From Noise to Order: Learning to Rank via Denoising Diffusion

arXiv:2602.11453v3 Announce Type: replace-cross Abstract: Learning-to-rank (LTR) methods have traditionally been limited to discriminative machine learning approaches that model the probability of the document being relevant to the query given some feature representation of the query-document pair. We propose an alternative denoising diffusion-based generative approach to LTR that instead models the full joint distribution over features and relevance labels. While in discriminative LTR, an over-parameterized ranking model may find different ways to fit the training data, we posit that candidate solutions that can explain the full data distribution under the generative setting maybe better at estimating relevance. Thus, we propose DiffusionRank that extends TabDiff, an existing diffusion model for tabular datasets, to create generative alternatives to classical discriminative pointwise and pairwise LTR objectives. Our work demonstrates improvements from DiffusionRank over discriminative counterparts on four standard LTR datasets and points to a rich space for future exploration to leverage ongoing advancements in deep generative models for LTR. Our code is publicly available at https://github.com/sadjadeb/DiffusionRank.

20.
arXiv (CS.CV) 2026-06-11

CoVEBench: Can Video Editing Models Handle Complex Instructions?

While recent text-guided video editing models excel at elementary tasks (e.g., style transfer, object insertion), real-world user requests are highly compositional. A single prompt often demands multiple coupled edits, such as modifying subjects, actions, and camera views, while strictly preserving unrelated spatiotemporal content. Existing benchmarks, heavily constrained by isolated edits and coarse global metrics, fail to diagnose how models handle such complex workflows. To address this gap, we introduce CoVEBench, a compositional video editing benchmark comprising 416 curated source videos, 626 multi-point editing instructions, and 9,990 fine-grained checklist items. Covering diverse editing dimensions, CoVEBench evaluates models via MLLM-judged instruction compliance and video fidelity, alongside automated metrics for video quality. Extensive experiments reveal that compositional editing remains a profound challenge: current models frequently omit edits, violate preservation constraints, or introduce artifacts when handling multiple operations simultaneously. CoVEBench provides a challenging, diagnostic testbed to advance video editing toward realistic user workflows.

21.
arXiv (CS.CV) 2026-06-18

HACMatch Semi-Supervised Rotation Regression with Hardness-Aware Curriculum Pseudo Labeling

Regressing 3D rotations of objects from 2D images is a crucial yet challenging task, with broad applications in autonomous driving, virtual reality, and robotic control. Existing rotation regression models often rely on large amounts of labeled data for training or require additional information beyond 2D images, such as point clouds or CAD models. Therefore, exploring semi-supervised rotation regression using only a limited number of labeled 2D images is highly valuable. While recent work FisherMatch introduces semi-supervised learning to rotation regression, it suffers from rigid entropy-based pseudo-label filtering that fails to effectively distinguish between reliable and unreliable unlabeled samples. To address this limitation, we propose a hardness-aware curriculum learning framework that dynamically selects pseudo-labeled samples based on their difficulty, progressing from easy to complex examples. We introduce both multi-stage and adaptive curriculum strategies to replace fixed-threshold filtering with more flexible, hardness-aware mechanisms. Additionally, we present a novel structured data augmentation strategy specifically tailored for rotation estimation, which assembles composite images from augmented patches to introduce feature diversity while preserving critical geometric integrity. Comprehensive experiments on PASCAL3D+ and ObjectNet3D demonstrate that our method outperforms existing supervised and semi-supervised baselines, particularly in low-data regimes, validating the effectiveness of our curriculum learning framework and structured augmentation approach.

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

Evaluation of Alternative-Based Information Systems for Deliberative Polling using an Agentic Simulator

arXiv:2606.11692v1 Announce Type: cross Abstract: Deliberative polling promises to improve collective decision-making by exposing shareholders to a broad range of arguments before they vote. Yet ensuring that every voter encounters a representative sample of the reason space, the coverage problem, remains an open challenge, particularly at scale and in adversarial or strategically motivated electorates. This paper introduces a way of evaluating solutions using the LLM-based Agentic Bipolar Argumentation Simulator, grounded in a framework which formalises a poll as a six-tuple of endorsing and opposing justifications, attack and enhance relations, and shareholder- and relation-weights. ABAS simulates N autonomous shareholder agents, each assigned a latent opinion according to desired distributions in [-1, 1], who sequentially vote, choose or author justifications, and optionally submit argumentation-graph links. The simulator implements recommendations that rank existing justifications by their observable endorsement mass. It evaluates the mechanism's success by coverage, namely the fraction of the corpus reason-tag set represented in the K recommendations presented to each shareholder, as a solution to the NP-hard Subsuming Justification Problem. Reported experiments characterise how creativity rate (pown), recommendation size (K), argumentation density (plinks), and population size (N) affect coverage and corpus diversity. In an authenticated electorate where Sybil attacks are impossible and only the relation graph is gameable, we stress-test the scoring with coordinated strategic voting attacks: a tag-flood attack collapses coverage, while author-count relation weighting through a reversed-PageRank rule resists the flood markedly better than uniform weights.

23.
medRxiv (Medicine) 2026-06-17

Macrophage-targeted glucocorticoid prodrug resolves acute inflammation while preserving HPA axis function: mechanistic, preclinical, and Phase II/III clinical evidence

Glucocorticoids (GCs) remain the fastest-acting anti-inflammatory agents but are constrained by systemic exposure that suppresses the hypothalamic pituitary adrenal (HPA) axis, silences adaptive immunity, and drives chronic toxicities. Chronic inflammatory diseases are sustained by long-lived CD206+ macrophages containing immune-resistant pathogenic material not cleared physiologically. We developed 101-PGC-005 ('005), a macrophage-targeted type 1a dexamethasone prodrug engineered for low-affinity, recycling-compatible uptake via CD206, with intracellular release triggered by acidic endosomes. We evaluated '005 in mechanistic assays, pathogen-diverse preclinical models, three human pharmacokinetic (PK) studies, and an adaptive-design randomized Phase II/III trial in 309 hospitalized patients with moderate COVID-19. In two completed Phase I human studies, a first-in-human dose-escalation and repeated-dose study and a dedicated single/multiple-dose PK and safety study; '005 circulated as intact prodrug with rapid systemic clearance (Tmax ~0.5 h; terminal half-life ~1.9 h), with no measurable free dexamethasone after single dosing and only low, clinically non-significant free dexamethasone after repeated dosing, and intact prodrug recovered unchanged in urine. Morning cortisol and ACTH were preserved after 30 mg once daily for three consecutive days (1.5 times the intended therapeutic dose). A cerebrospinal fluid PK study is evaluating central-compartment penetration. In the Phase II/III trial, powered for non-inferiority, conducted across six sites in India under GCP with Ministry of Health approval and independent DSMB oversight; '005 (20 mg IV daily for 3 days) was superior to dexamethasone (6 mg IV daily for 3 -10 days) on the primary endpoint of time to > a 2-point improvement on the WHO ordinal scale (HR 2.31; 95% CI 1.83-2.93; p < 0.0001; median 3 vs. 4 days). '005 was also superior on viral clearance (HR 1.47; 95% CI 1.17-1.84; p = 0.0001), hospital discharge rate, SpO2; recovery, and fever resolution. Zero patients in the '005 arm received investigator-initiated corticosteroid supplementation despite protocol allowance. All 309 randomized patients completed the study (ITT = per-protocol). Safety profiles were equivalent (TEAEs 54.8% vs 54.5%; p = 0.958), with no Grade 3+ events, SAEs, deaths, or discontinuations in either arm. Mechanistically, '005 delivered dual benefit: acute debulking of inflammatory macrophages and selective depletion of chronically activated pathology-sustaining macrophages, while preserving CXCL10 antiviral signaling and physiologic HPA control. Critically, HPA preservation is not merely a safety feature, it is a core efficacy mechanism: by clearing the pathogenic macrophage burden that was overriding HPA regulation, '005 restores the conditions for endogenous cortisol to resume its pulsatile, demand-responsive anti-inflammatory role across all GR-expressing cells, lymphocytes, endothelial cells, neurons, and newly differentiated macrophages, that '005 itself cannot reach. These findings support regulatory-grade evidence for macrophage-targeted corticosteroid therapy and provide the foundation for further development across acute inflammatory indications (sepsis, viral pneumonia, cytokine-release syndromes) and chronic macrophage-driven diseases (atherosclerosis, metabolic steatohepatitis, neurodegeneration, tumor-associated macrophages).

24.
arXiv (CS.CL) 2026-06-19

A Survey of On-Policy Distillation for Large Language Models

As Large Language Models continue to grow in both capability and cost, transferring frontier capabilities into smaller, deployable students has become an important engineering problem, and knowledge distillation remains a common technique for this transfer. The prevailing recipe in industrial pipelines, static imitation of teacher-generated text, carries a structural weakness that grows more severe as tasks become longer and more reasoning-intensive. Because the student is trained on flawless teacher prefixes but generates its own at inference, small errors tend to accumulate into trajectories it has rarely been trained to recover from, and the resulting exposure bias has been shown to scale roughly with the square of sequence length. On-Policy Distillation reorganizes the training loop around this observation by having the teacher provide feedback on what the student actually produces, with the goal of reducing the compounding term toward linear and reframing distillation as an iterative correction process rather than single-pass imitation. The resulting literature has expanded along divergence design, reward-guided optimization, and self-play, yet contributions remain scattered across the knowledge distillation, RLHF, and imitation learning communities without a unified treatment. This survey provides such a treatment. We formalize OPD as f-divergence minimization over student-sampled trajectories, organize the field along three design axes (what to optimize, where the signal comes from, and how to stabilize training in practice), and consolidate success conditions, recurring failure modes, and the connection between OPD and KL-constrained reinforcement learning. We close with open problems that emerge from this synthesis, including distillation scaling laws, uncertainty-aware feedback, agent-level distillation, and the growing overlap between knowledge distillation and RL.

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

A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models

arXiv:2606.17417v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) achieve strong performance on a variety of audio understanding tasks but continue to struggle with temporal reasoning, a fundamental capability central to human auditory perception. Understanding the causes of these failures remains challenging as existing benchmarks report performance gaps without probing underlying mechanisms. To address this, we introduce a benchmark with 1,657 questions across three foundational tasks designed specifically for mechanistic analysis. Examining model outputs across varying input settings (behavioral analysis) reveals that models often under-utilize audio when textual cues are available. We also provide the first causal mechanistic analysis of temporal reasoning failures in LALMs. Comparing attention upweighting against scaling, we find that redistributing attention across audio tokens is more effective than increasing audio attention. Targeting task-relevant tokens yields further gains. These findings suggest that modality imbalance alone cannot explain failures. Attention scaling at bottleneck layers improves accuracy from 55.9% to 59.1% without fine-tuning, demonstrating a promising direction for future work.