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.
Nature (Science) 2026-06-22

C-glycoside synthesis via radical cross-coupling of glycohydrazides

作者:

Carbohydrates are among the most abundant and structurally diverse biomolecules in nature, playing central roles in energy storage, molecular recognition, and cell signaling. Within this domain, C-glycosides1-3, in which the oxygen atom of the glycosidic bond in O-glycosides is replaced by carbon, have emerged as valuable motifs in medicinal chemistry due to their resistance to enzymatic hydrolysis2,4. Of particular importance are C-aryl glycosides, exemplified by the SGLT2 inhibitors dapagliflozin, canagliflozin, and empagliflozin, which are frontline therapies for type 2 diabetes5-7. However, scalable syntheses of C-aryl glycosides have traditionally relied on protected sugar derivatives, lengthy sequences, or conventional cross-couplings that often suffer from poor selectivity, limited scope, and extensive protecting-group manipulation6. Herein, we report a practical approach to C-aryl glycosides using glycosyl sulfonyl hydrazides as redox-neutral radical precursors for cross-coupling. Prepared directly from unprotected native sugars, these reagents generate glycosyl radicals under mild conditions and enable efficient access to diverse C-aryl glycosides, including all approved SGLT2 inhibitors, natural products such as salmochelins and neopetrosins, and medicinally relevant probes. Beyond anomeric functionalization, this platform enables C–C bond formation at multiple positions on carbohydrate scaffolds and supports stereoretentive radical coupling that can override inherent stereochemical biases, expanding practical access to carbohydrate-derived therapeutics and chemical tools.

02.
arXiv (CS.AI) 2026-06-16

LLM Jaggedness Unlocks Scientific Creativity

arXiv:2605.10574v3 Announce Type: replace Abstract: As artificial intelligence advances, models are not improving uniformly. Instead, progress unfolds in a jagged fashion, with capabilities growing unevenly across tasks, domains, and model scales. In this work, we examine this dynamic jaggedness through the lens of scientific idea generation. We introduce SciAidanBench, a benchmark of open-ended scientific questions designed to measure the scientific creativity of large language models (LLMs). Given a scientific question, models are asked to generate as many unique and coherent ideas as possible, with the total number of valid responses serving as a proxy for creative potential. Evaluating 19 base models across 8 providers (30 total variants including reasoning versions), we find that jaggedness manifests both across models and within models. First, in a cross-task comparison between general and scientific creativity, improvements in general creativity do not translate uniformly to scientific creativity, revealing divergent capability profiles across models. Second, at the prompt level, stronger models do not improve uniformly; instead, they exhibit high variability, with bursts of creativity on some questions and limited performance on others. Third, at the domain level, individual models display uneven strengths across scientific subfields, reflecting fragmented internal capability profiles. Finally, we show that this jaggedness can be harnessed. We explore mechanisms of inference-time compute, knowledge pooling, and brainstorming to combine models effectively and construct meta-model ensembles that outperform any single model. Our results position jaggedness not as a limitation, but as a resource, a structural feature of AI progress that, when understood and leveraged, can amplify LLM-driven scientific creativity.

03.
arXiv (CS.CV) 2026-06-16

Through-Foliage Surface-Temperature Reconstruction for Early Wildfire Detection

We present a method to reconstruct surface temperatures through forest vegetation by combining signal processing and machine learning, enabling fully automated aerial wildfire monitoring with drones for early fire detection. Synthetic aperture (SA) sensing reduces canopy occlusion but introduces thermal blur. To overcome this, we train a visual state space model to recover subtle thermal signals of partially occluded soil and fire hotspots from blurred data. To address limited real-world training data, we generate realistic surface temperature simulations using a latent diffusion model, temperature augmentation, and procedural thermal forest modeling. On simulated datasets, our method reduces RMSE by 2-2.5 versus conventional thermal and uncorrected SA imaging; in field experiments on hotspots, RMSE improved by 12.8-fold and 2.6-fold, respectively. Our approach also generalizes to other thermal signals, including human signatures, capturing morphology and extent – critical where simple thresholding fails – while conventional imaging struggles with partial occlusion.

04.
arXiv (CS.CV) 2026-06-16

A Human-in-the-Loop Label Error Detection Framework Applied to Arabic-Script HTR Datasets

Despite recent advances, Handwritten Text Recognition (HTR) for Arabic-script languages still lags behind Latin-script HTR. Part of the problem is dataset quality. To help closing this gap, we propose a two-stage framework (CER-HV) for detecting label errors. Stage 1 (CER) is a Character-Error-Rate-based noise detector built on a Convolutional Recurrent Neural Network (CRNN) architecture. Stage 2 (HV) is the Human-In-The-Loop (HITL) Verification of noisy samples detected by the first stage. Applying the CER-HV framework on multiple Arabic-script datasets can identify samples with label errors including transcription, segmentation, orientation, and non-text content errors that can markedly affect HTR performance. These errors were identified by the first stage of the framework with up to 90percent (top-50) precision. We also show that our CRNN achieves state-of-the-art performance across five of the six evaluated datasets, reaching 8.46 percent Character Error Rate (CER) on KHATT (Arabic), 8.22 percent on PHTI (Pashto), 10.59 percent on Ajami, and 10.11% on Muharaf (Arabic), all without any data cleaning. We establish a new baseline of 11.3 percent CER on the PHTD (Persian) dataset. Applying CER-HV improves evaluation CER by up to 1.8 percentage points after dataset cleaning and retraining. Although our experiments focus on documents written in an Arabic-script language, the framework is general and can be applied to other text recognition datasets

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

Dynamic Black-hole Emission Tomography with Physics-informed Neural Fields

With the success of static black-hole imaging, the next frontier is the dynamic and 3D imaging of black holes. Recovering the dynamic 3D gas near a black hole would reveal previously-unseen parts of the universe and inform new physics models. However, only sparse radio measurements from a single viewpoint are possible, making the dynamic 3D reconstruction problem significantly ill-posed. Previously, BH-NeRF addressed the ill-posed problem by assuming Keplerian dynamics of the gas, but this assumption breaks down near the black hole, where the strong gravitational pull of the black hole and increased electromagnetic activity complicate fluid dynamics. To overcome the restrictive assumptions of BH-NeRF, we propose PI-DEF, a physics-informed approach that uses differentiable neural rendering to fit a 4D (time + 3D) emissivity field given EHT measurements. Our approach jointly reconstructs the 3D velocity field with the 4D emissivity field and enforces the velocity as a soft constraint on the dynamics of the emissivity. In experiments on simulated data, we find significantly improved reconstruction accuracy over both BH-NeRF and a physics-agnostic approach. We demonstrate how our method may be used to estimate other physics parameters of the black hole, such as its spin.

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

ParaScale: Scale-Calibrated Camera-Motion Transfer via a Gauge-Invariant Parallax Number

作者:

arXiv:2606.19805v1 Announce Type: cross Abstract: Transferring the camera motion of a reference video to a freshly generated one lets creators reuse cinematic moves. Yet reference and target often live at incompatible scales – a sweep across a galaxy versus a nudge across a desk – and naively reusing the recovered trajectory yields either imperceptible or violently exaggerated motion. We trace this to a geometric fact: translation-induced image motion scales as ||T||/Z, so a monocular trajectory is meaningful only up to a depth-scale gauge. We distill this into the Parallax Number Pi = ||Delta T|| / Zbar, a dimensionless, gauge-invariant descriptor of how strongly a camera move is felt, and prove that it – not the raw trajectory – is the quantity that scale-faithful transfer must preserve. ParaScale is a plug-and-play module that reads Pi off any reference video and re-realizes it against the target scene's own depth, per frame, leaving rotation untouched. Sitting between pose extraction and pose injection, it requires no retraining and drops into any pose-conditioned generator. We further introduce the Parallax Consistency Error (PCE), a scale-symmetric metric that – unlike the similarity-aligned TransErr – exposes scene-scale mismatch. Across scale regimes spanning four orders of magnitude and multiple backbones, ParaScale keeps the realized parallax on the identity line and cuts PCE by more than 3x over uncalibrated transfer with no loss of visual fidelity.

07.
arXiv (CS.CL) 2026-06-16

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD). Nemotron 3 Ultra is our most capable model yet, employing multiple key technologies - LatentMoE, Multi Token Prediction (MTP), NVFP4 pre-training, multi-environment RLVR, MOPD, and reasoning budget control. Nemotron 3 Ultra achieves up to ~6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy. The state-of-the-art accuracy, high inference throughput, and 1M token context length make Nemotron 3 Ultra ideal for long-running autonomous agentic tasks. We open-source the base, post-trained, and quantized checkpoints, along with the training data and recipe on HuggingFace.

08.
arXiv (CS.LG) 2026-06-17

ResAware: Cross-Environment Website Fingerprinting via Resource-Privileged Distillation

arXiv:2606.17462v1 Announce Type: new Abstract: While Website Fingerprinting (WF) attacks achieve high accuracy in controlled laboratory settings, they often degrade substantially in real-world environments due to spatio-temporal drift, browser heterogeneity, proxy obfuscation and etc. This limitation stems from their sole reliance on low-level traffic features that are noisy and highly sensitive to environmental perturbations. To address this problem, we propose ResAware, a cross-environment resource-aware distillation framework under a training-rich/inference-poor asymmetric setting. Specifically, ResAware trains a teacher model on resource-level features, and then distills the resulting privileged knowledge into a student model through heterogeneous knowledge distillation. At deployment time, the student model performs inference using only encrypted traffic, incurring zero additional cost. We evaluate ResAware on a large-scale dataset collected over five months from six globally distributed vantage points, comprising more than $160{,}000$ paired samples. The results show that ResAware significantly enhances the cross-environment robustness of diverse WF baselines. Under a 150-day temporal drift, for example, ResAware improves the F1-score of Var-CNN from $72.77\%$ to $81.49\%$ and the open-world $TPR@1\%FPR$ from $22.40\%$ to $27.20\%$. Our results demonstrate that resource-level supervision improves WF robustness without expanding online observation capabilities.

09.
arXiv (CS.LG) 2026-06-15

ORCA: A Platform for Open-Source Dexterity Research

arXiv:2606.14561v1 Announce Type: cross Abstract: Robotics manipulation research increasingly focuses on two-finger parallel grippers for their effectiveness, affordability, and ease of teleoperation. Grippers are nonetheless limited by their form factor, often requiring bimanual setups even for simple reorientation tasks. Anthropomorphic hands are a more natural platform for dexterous robot learning – closer to the human hand, and capable of learning from human video – yet they remain hard to use in learning research: even where open and accessible hand hardware exists, the software for control, simulation, teleoperation, and retargeting is scattered in one-off code bases, and largely disconnected from the robot-learning ecosystem. In this work, we introduce the \orca~learning stack, an open-source research stack for dexterity as a first-class robot learning domain. Our \orca~stack unifies low-level control, simulation, teleoperation from a range of consumer platforms, and hand retargeting, behind a single interface, and integrates natively with popular robot-learning frameworks such as \lerobot, so dexterous hand researchers can leverage the same data, training, and evaluation pipelines used for non-dexterous robot learning. We demonstrate a complete end-to-end workflow, collecting expert demonstrations of an in-hand reorientation task by teleoperation with a consumer-grade VR headset, training an autonomous policy with \lerobot, and evaluating the learned policy in a fully reproducible and observable setup. We open-source the entire stack as a shared, reproducible foundation for dexterous-manipulation research.

10.
medRxiv (Medicine) 2026-06-22

Associations of Chemical Exposures with Psychological Distress and Depression Diagnosis among Waste Pickers in Brasilia, Brazil: A Cross-Sectional Study

Introduction: Waste pickers face chemical exposures. We evaluated whether chemical exposure is associated with psychological distress and depression. Methods: A 2017 cross-sectional survey included 1,141 waste pickers working in the Estrutural open dump in Brasilia, Brazil. Participants self-reported occupational exposure to 11 chemical categories, 17 psychological distress symptoms, and depression diagnoses. Associations of chemical exposure with mean psychological distress scores and depression prevalence were assessed, adjusted for age, sex, marital status, and income. Results: Mean psychological distress score was higher among those exposed to any chemical (mean of 8.1 vs 6.1; adjusted mean difference [aMD]: 1.8 [0.9, 2.7]) and higher among those exposed to each of 11 chemical categories, for example, smoke (aMD: 1.2 [0.6, 1.7]), batteries (aMD: 1.5 [1.0, 1.9], and oils (aMD: 1.3 [0.9, 1.8]). Depression was more prevalent among those exposed to oils (16.6% vs 10.6%; adjusted prevalence difference [aPD]: 6.3% [95% CI: 2.3, 10.2]), cleaning products (aPD: 5.4% [1.2, 9.5]), medications (aPD: 4.7% [0.6, 8.8]), and aerosols (aPD: 5.3% [1.3, 9.3]) but, not smoke, batteries, greases, insecticides, solvents, paints, chemical containers, or any chemical. Conclusion: These associations highlight the need to consider policy level protections for waste pickers to reduce chemical exposure and guard against psychological distress. Further research is necessary to explore which specific chemicals, within broad chemical categories, are associated with psychological distress and depression.

11.
arXiv (CS.CL) 2026-06-16

ACCORD: Action-Conditioned Contextual Grounding for Language Agents

User instructions are often underspecified because humans rely on implicit assumptions about the surrounding environment. For large language model (LLM) agents operating in information-rich digital and physical environments, these assumptions cannot be inferred from the instruction alone; they must be recovered from the current state of tools, data, interfaces, and observations. Effective execution therefore requires agents to identify missing context, ground it in observed evidence, and carry it forward into subsequent actions. We show that current agents often fail to do so. They act from assumed rather than observed specifics, overlook information they could have gathered, and fail to incorporate evidence that has already been returned. Building on this insight, we propose ACCORD (Action-Conditioned Contextual Grounding), a simple and effective agent framework for adaptive grounding. Before each action, ACCORD actively probes the environment for missing information and integrates relevant context from the agent's trajectory that would otherwise be overlooked. Requiring no additional training or task-success signals, ACCORD improves task-goal completion on AppWorld by up to +20.6 points with GPT-5-mini, from 42.0% to 62.6%, compared to strong baselines. These gains persist with a substantially stronger base model (+10.8 with Claude-4.5-sonnet), an open-weight model (+10.1 with Qwen3.5-27B-FP8), and on the embodied AlfWorld benchmark (+7.4 success rate with GPT-5-mini).

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

TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization

arXiv:2606.13054v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment. Ternarization has emerged as a promising compression technique, offering significant reductions in model size and inference complexity. However, existing methods struggle with heavy-tailed activation distributions and therefore keep activations in high precision, fundamentally limiting end-to-end inference acceleration. To overcome this limitation, we propose TWLA, a post-training quantization (PTQ) framework that achieves 1.58-bit weight compression and 4-bit activation quantization while maintaining high accuracy. TWLA comprises three components: (1) Euclidean-to-Manifold Asymmetric Ternary Quantizer (E2M-ATQ) minimizes layer-output error under weight ternarization via a two-stage optimization from Euclidean initialization to manifold relocation; (2) Kronecker Orthogonal Tri-Modal Shaping (KOTMS) applies a Kronecker-structured orthogonal rotation to reshape weights into ternary-friendly tri-modal distributions, while the shared rotation statistically suppresses activation outliers; and (3) Inter-Layer Aware Activation Mixed Precision (ILA-AMP) explicitly introduces adjacent-layer second-order interaction costs in bit allocation and jointly optimizes for the layer-wise disparity of activation quantization gains induced by the shared orthogonal transform, preventing cascades triggered by a few weak layers. Extensive experiments demonstrate that TWLA maintains high accuracy under W1.58A4, while delivering significant inference acceleration. The code is available at .

13.
arXiv (CS.AI) 2026-06-11

Improving Detection of Rare Nodes in Hierarchical Multi-Label Learning

arXiv:2602.08986v2 Announce Type: replace-cross Abstract: In hierarchical multi-label classification, a persistent challenge is enabling model predictions to reach deeper levels of the hierarchy for more detailed or fine-grained classifications. This difficulty partly arises from the natural rarity of certain classes (or hierarchical nodes) and the hierarchical constraint that ensures child nodes are almost always less frequent than their parents. To address this, we propose a weighted loss objective for neural networks that combines node-wise imbalance weighting with focal weighting components, the latter leveraging modern quantification of ensemble uncertainties. By emphasizing rare nodes rather than rare observations (data points), and focusing on uncertain nodes for each model output distribution during training, we observe improvements in recall by up to a factor of five on benchmark datasets, along with statistically significant gains in $F_{1}$ score. We also show our approach aids convolutional networks on challenging tasks, as in situations with suboptimal encoders or limited data.

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

Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering

Full-duplex spoken language models (FD-SLMs) enable seamless speech interaction by allowing models to listen and speak simultaneously, yet the internal mechanism by which they coordinate listening and speaking remains underexplored. We analyze the predictive behavior encoded in FD-SLM hidden representations and find that they exhibit stream-specific predictive patterns: during listening, they preferentially predict the incoming user stream, whereas during speaking, they preferentially predict the model output stream. Building on this observation, we show that FD-SLMs dynamically modulate their internal predictive focus between two states: a generative state aligned with model output generation and a perceptive state aligned with incoming user input. However, this modulation can lag behind abrupt changes in conversational context. During user interruptions, the model remains transiently biased toward the generative state before transitioning into the perceptive state, causing it to miss the beginning of the incoming input. We term this delayed internal transition state inertia. To quantify its downstream impact, we introduce the Zero-Buffer Benchmark (ZBB), a diagnostic benchmark for evaluating immediate interruption comprehension when user speech begins abruptly. We evaluate this setting using response correctness and initial-word occurrence rate (IWOR). Finally, we mitigate state inertia through activation steering with a perception vector, a training-free intervention with little additional computational overhead. Across multiple state-of-the-art FD-SLMs, activation steering substantially improves interruption handling; for example, on PersonaPlex, it improves correctness from 28% to 45% and IWOR from 40% to 72% without any fine-tuning.

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

QIAS 2026: Overview of the Shared Task on Islamic Inheritance Reasoning

This paper presents a comprehensive overview of the QIAS 2026 shared task, organized as part of the OSACT7 Workshop and co-located with LREC 2026. The shared task was designed to evaluate the ability of large language models to perform complex reasoning in the religious and legal domain of Islamic inheritance. Unlike conventional question-answering benchmarks, QIAS 2026 focuses on end-to-end reasoning from natural language cases, requiring systems to perform the full inheritance calculation process, from identifying the eligible heirs to assigning the correct share to each beneficiary. To support this evaluation, the task was based on the MAWARITH benchmark, a dataset of $12{,}500$ Arabic inheritance cases annotated with intermediate reasoning steps and final answers. System submissions were evaluated using MIR-E, a multi-step metric that measures performance across the main stages of inheritance reasoning. A total of $16$ teams participated in the shared task, investigating a range of approaches, including prompting-based methods, retrieval-augmented generation, and fine-tuning strategies. The results show that Islamic inheritance remains a highly challenging benchmark for current language models, especially in stages that require precise legal interpretation and structured numerical reasoning. This overview summarizes the task design, dataset, evaluation framework, participating systems, and main results.

16.
arXiv (CS.LG) 2026-06-11

Finding Multiple Interpretations in Datasets

arXiv:2606.12277v1 Announce Type: new Abstract: In this paper, we propose an approach to finding sets of similar-performing models (in terms of loss/accuracy measurements) with highly different context-aware characteristics. Through experiments on the METABRIC dataset, we show that the proposed method finds multiple models with highly different gene expressions than those found by the control methodology without performance penalties. We argue that the proposed methodology is important whenever one aims to analyze any global characteristic of a model to extract insight into the underlying phenomenon being studied.

17.
Nature (Science) 2026-06-10

SIRT7 regulates dosage compensation and safeguards the female X chromosome

Sirtuins are deacetylases implicated in stress responses and longevity in mammals1,2. Although their differential impact on disease for the two sexes has been noted3–7, the underlying reasons are unclear. Here, using Sirt7 as a model in mice, we examine the mechanisms leading to sex differences and find that Sirt7−/− female mice have decreased fitness throughout their lifespan. Notably, SIRT7 preferentially localizes to the sex chromosomes. In female individuals, SIRT7 loss affects X-chromosome inactivation, the first arm of dosage compensation that equalizes X-linked gene expression between males and females8–10. Xist is overexpressed and gene silencing becomes more efficient. However, SIRT7 loss has greatest impact on the active X (Xa) chromosome. The Xa chromosome becomes hyperacetylated at Lys36 of histone H3, structurally disorganized, prone to DNA damage and overexpressed. Increased Xa-chromosome expression leads to genome imbalance and augmented X-chromosome upregulation—the second arm of dosage compensation that balances X-chromosome versus autosomal gene expression. These data reveal an essential crosstalk between sirtuins and the sex chromosomes, with SIRT7 safeguarding X-chromosome integrity and dosage balance with autosomes. We propose that the sex bias in SIRT7 biology can be explained in part by unequal effects on the sex chromosomes. SIRT7 safeguards X-chromosome integrity and dosage balance with autosomes.

18.
arXiv (CS.AI) 2026-06-19

RIVET: Robust Idempotent Voice Attribute Editing

arXiv:2606.19629v1 Announce Type: cross Abstract: Voice attribute editing models modify characteristics such as age and gender while preserving speaker identity. In large-scale speech datasets, however, attribute annotations are often noisy or inconsistent, which can cause conditional generative models to produce unstable edits. In this work, we show that idempotency provides an effective mechanism for improving robustness to noisy labels. An idempotent operator is one for which repeated application does not change the result, i.e., f(f(x)) = f(x). Enforcing this property acts as an implicit regularizer that reduces sensitivity to mislabeled examples. We introduce RIVET, a training framework that incorporates an idempotency objective to improve robustness to label noise. We evaluate RIVET under controlled label noise and on the GLOBE dataset with naturally noisy annotations. RIVET improves editing success and better preserves speaker identity than standard training, showing that idempotency improves robustness in voice editing models.

19.
arXiv (CS.CV) 2026-06-16

CogCanvas: A Benchmark for Evaluating Multi-Subject Reference-Based Image Generation

Multi-subject reference-based image generation requires jointly preserving multiple human identities, binding per-person objects and fashion items, and respecting a specified background scene, a regime where current diffusion models remain brittle. Existing benchmarks evaluate only one axis at a time and none jointly captures multi-identity composition with human-object interaction, background grounding, and spatial plausibility. We introduce CogCanvas, a benchmark of 1,952 curated reference images spanning 100 celebrity identities, 115 distinctive objects and fashion items, and 29 real-world background scenes including landmarks, from which we construct 1,361 compositional prompts covering 2-5 person group sizes. The curation pipeline combines DINOv2-based deduplication, two-stage aesthetic filtering, and automated derivation of structured interaction and position graphs that serve as ground-truth supervision. CogCanvas supports three tasks, reference-based multi-human-object generation (primary), text-to-image compositional generation, and reference retrieval, under a unified six-axis evaluation protocol. We introduce two metrics tailored to the multi-reference setting: BG-Sim, which scores background fidelity on SAM 3-masked regions via DINOv3 feature similarity, and Attr-VQA, which uses a multimodal LLM to verify per-subject attribute binding and inter-person interactions against the structured graphs. Benchmarking five SOTA methods reveals that every model degrades substantially as group size grows from 2 to 5, with near-complete failure on object/fashion binding beyond three subjects.

20.
arXiv (CS.CL) 2026-06-19

DeFrame: Debiasing Large Language Models Against Framing Effects

As large language models (LLMs) are increasingly deployed in real-world applications, ensuring their fair responses across demographics has become crucial. Despite many efforts, an ongoing challenge is hidden bias: LLMs appear fair under standard evaluations, but can produce biased responses outside those evaluation settings. In this paper, we identify framing – differences in how semantically equivalent prompts are expressed (e.g., "A is better than B" vs. "B is worse than A") – as an underexplored contributor to this gap. We first introduce the concept of "framing disparity" to quantify the impact of framing on fairness evaluation. By augmenting fairness evaluation benchmarks with alternative framings, we find that (1) fairness scores vary significantly with framing and (2) existing debiasing methods improve overall (i.e., frame-averaged) fairness, but often fail to reduce framing-induced disparities. To address this, we propose a framing-aware debiasing method that encourages LLMs to be more consistent across framings. Experiments demonstrate that our approach reduces overall bias and improves robustness against framing disparities, enabling LLMs to produce fairer and more consistent responses.

21.
arXiv (CS.CV) 2026-06-16

Conditional Multi-Event Temporal Grounding in Long-Form Video

Multimodal large language models have made rapid progress in video temporal grounding, yet real-world applications routinely require localizing every event that satisfies compositional temporal and spatial conditions. Existing benchmarks fall short: they localize only a single moment per query, count without temporal conditions, or treat grounding and counting as disjoint tasks. We introduce CoMET-Bench for Conditional Multi-Event Temporal Grounding in long-form video, comprising 2789 queries over 600 videos averaging 33.8 minutes across five real-world domains, with each query composed from 4 temporal conditions, 3 spatial conditions, and a dedicated negative-query subset. We further propose a unified evaluation protocol jointly measuring counting, grounding, and negative-query recognition, including a new Rejection-F1 metric that prevents trivial gaming by lazy "always-empty" models. Benchmarking a broad suite of MLLMs, agent-based, and grounding-specialized methods reveals that existing approaches remain far from solving this task. Building on these findings, we propose CoMET-Agent, a training-free agentic framework that reformulates the task as structured search-and-aggregate, improving F1@0.5 by 6.1% over GPT-5 purely through structural reasoning. Failure analysis further surfaces three open directions: fine-grained entity tracking, position-uniform retrieval, and causal event pairing.

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

Bridging the Morphology Gap: Adapting VLA Models to Dexterous Manipulation via Intent-Conditioned Fine-Tuning

arXiv:2606.12109v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable zero-shot generalization in robotic manipulation, yet the vast majority of pre-trained pipelines remain strictly confined to low-DoF parallel grippers. Adapting these rich semantic priors to high-DoF dexterous hands introduces a severe morphology gap, direct end-to-end joint fine-tuning inherently causes catastrophic forgetting of spatial reasoning and acute action manifold collapse due to data scarcity. In this paper, we present InDex, a novel, data-efficient adaptation framework rooted in cross-morphology semantic inheritance. Rather than discarding the pre-trained 1-DoF parallel grasp output, we repurpose it as a continuous, macroscopic virtual grasp intent proxy to sequentialize the control topology. We implement a two-stage decoupled learning architecture: the first stage parameter-efficiently aligns the VLA backbone to predict continuous arm trajectories and the scalar grasp intent; the second stage freezes this spatial backbone and leverages an intent-conditioned denoising diffusion head to decode fine-grained joint articulations for multi-fingered end-effectors. Extensive simulation benchmarks across a suite of multi-stage, contact-rich dexterous manipulation tasks demonstrate that InDex effectively masters intricate skills with minimal demonstration data, substantially outperforming monolithic baselines while preserving the robust spatial generalizability of the original VLA prior.

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

Gaze Heads: How VLMs Look at What They Describe

How a vision-language model internally solves the task of describing an image is far from obvious. We find that the model develops a specific mechanism for this: a small set of attention heads in its language-model backbone, which we call gaze heads, whose attention tracks the image region the model is currently describing. We find them with a simple correlation score from a few forward passes, using comic strips as a controlled testbed where narrative order is laid out spatially. These gaze heads do not just track the image tokens being described: redirecting their attention to a chosen region forces the VLM to describe that region instead. A single attention-mask intervention on the top-100 gaze heads, fewer than 9% of all heads, steers the model's answer to any chosen comic panel at 83.1% accuracy, while the same intervention on random heads fails to redirect the answer, and intervening on all heads destroys generation. The same lever also extends to continuous control: switching the gaze target mid-generation makes the model wrap up its current panel description and move to the new one within a few tokens. Beyond comics, the same intervention redirects answers to chosen regions in natural COCO images. The mechanism further recurs across model sizes from 2B to 32B parameters and across other VLM architectures, although some frozen-encoder families show no comparable head set. More broadly, this shows that targeted edits identified through mechanistic analysis can serve as practical inference-time levers for steering multimodal model behavior, without any retraining. Our code, interactive demo, and datasets are available at https://gaze.baulab.info/

24.
arXiv (CS.CL) 2026-06-11

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application

Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities. Despite this importance, existing work lacks a systematic categorization and deep analysis. This paper systematically studies current researches on agentic environments from the perspective of the environment engineering lifecycle, covering their modeling, synthesis, evaluation and application. Specifically, the paper first introduces representative environments from the perspectives of eight attributes and eight domains, providing detailed analyses of their development paths and highlighting their core capabilities. Second, for automated environment synthesis, two paradigms are introduced, such as symbolic synthesis and neural synthesis. This paper also shows different environment evaluation methods in each paradigm. Thirdly, the corresponding environment applications from the perspective of agent-environment co-evolution are discussed. In specific, the paper characterizes the primary pathways for agent evolution in dynamic environments from four complementary perspectives: memory-centric experience evolution, orchestration-centric workflow evolution, trajectory-centric offline evolution, and exploration-centric online evolution. And three paradigms of environment evolution are identified, namely neural-driven, difficulty-driven, and scaling-driven approaches. At last, several promising future directions are discussed, including Environment-as-a-Service, Multi-agent Environments, and Neural-Symbolic Environments.

25.
arXiv (CS.AI) 2026-06-19

Charting the Future of Scholarly Knowledge with AI: A Community Perspective

arXiv:2509.02581v2 Announce Type: replace-cross Abstract: Despite the growing availability of tools designed to support scholarly knowledge extraction and organization, many researchers still rely on manual methods, sometimes due to unfamiliarity with existing technologies or limited access to domain-adapted solutions. Meanwhile, the rapid increase in scholarly publications across disciplines has made it increasingly difficult to stay current, further underscoring the need for scalable, AI-enabled approaches to structuring and synthesizing scholarly knowledge. Various research communities have begun addressing this challenge independently, developing tools and frameworks aimed at building reliable, dynamic, and queryable scholarly knowledge bases. However, limited interaction across these communities has hindered the exchange of methods, models, and best practices, slowing progress toward more integrated solutions. This manuscript identifies ways to foster cross-disciplinary dialogue, identify shared challenges, categorize new collaboration and shape future research directions in scholarly knowledge and organization.