Recognizing Co-Speech Gestures in-the-Wild
arXiv:2605.31589v2 Announce Type: replace Abstract: While humans naturally gesture during speech, only a sparse subset of these co-speech gestures are visually depictive and semantically linked to…
Latest
TransSLR: A Lightweight Transformer for Sign Language Recognition
arXiv:2608.06407v1 Announce Type: new Abstract: Automated Sign Language Recognition for under-represented languages remains a largely unsolved problem. Central African Sign Language (CASL) exemplifies this gap: the…
Test-Time Adaptation with Online Personalized Energy-Based Cache for Fine-Grained Video Expression Recognition
arXiv:2608.06467v1 Announce Type: new Abstract: Facial expression recognition (FER) in videos is challenging because models must identify subtle, temporally evolving affective states that vary across individuals.…
InsertFuse: A Unified Framework for Multi-Category Reference-Guided Image Insertion
arXiv:2608.06490v1 Announce Type: new Abstract: We present InsertFuse, a unified framework for multi-category reference-guided image insertion. Its key idea is to decouple category-specific expertise learning from…
Toward surface-based registration of a virtual preoperative cutting guide onto the mandible for reconstruction surgery
arXiv:2608.06599v1 Announce Type: new Abstract: Mandibular reconstruction restores facial continuity and oral function after segmental resection. Patient-specific cutting guides transfer a computed tomography (CT)-based plan to…
Improving Low-Resolution Face Recognition under Limited Data: How Synthetic Data Generation Can Close the Domain Gap
arXiv:2608.06580v1 Announce Type: new Abstract: Face Recognition (FR) systems in surveillance settings often encounter Low Resolution (LR) faces, those whose face region falls below the standard…
Do 3D Medical Foundation Models See Through MRI Artifacts? A Controlled Study of Representation Robustness
arXiv:2608.06613v1 Announce Type: new Abstract: Self-supervised 3D medical foundation models are increasingly used as general-purpose feature extractors, yet their sensitivity to MRI artifacts remains poorly understood.…
SLED: Scalable Location Encoding via Distillation
arXiv:2608.06612v1 Announce Type: new Abstract: The plethora of readily available geospatial data offers exciting opportunities to learn high quality representations of the planet, but the sheer…
WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA
arXiv:2608.01035v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely constrained by…
SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding
arXiv:2608.05137v2 Announce Type: replace Abstract: Understanding 3D scenes is fundamental to embodied intelligence, requiring joint reasoning over heterogeneous information from multiple modalities, including visual and geometric…
An AI4AI Framework for Visual Token Pruning
arXiv:2608.07193v1 Announce Type: cross Abstract: Visual-token pruning can substantially reduce the inference cost of multimodal large language models (MLLMs), yet existing methods largely rely on fixed,…
Walkable to Whom? Capturing Subjective Variability in Walkability Perception Using Multimodal Deep Learning
arXiv:2608.06934v1 Announce Type: cross Abstract: Visual perception of walkability varies substantially across individuals, reflecting differences in personal characteristics, experiences, and preferences. Existing studies, however, often reduce…
HFS: Holistic Query-Aware Frame Selection for Efficient Video Understanding
arXiv:2512.11534v2 Announce Type: replace Abstract: Key frame selection is essentially a set-level optimization problem: the quality of the selected subset depends on the interactions among frames,…
PURe: A Plug-and-Play Product-Unit Residual Module for Vision Networks
arXiv:2505.04397v3 Announce Type: replace Abstract: Modern vision networks are dominated by additive local transformations, whereas explicit multiplicative local interactions remain underexplored. Product units offer a direct…
Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models
arXiv:2604.11240v2 Announce Type: replace Abstract: Token pruning has emerged as an effective approach to reduce the substantial computational overhead of Large Vision-Language Models (LVLMs) by discarding…
Pre-Inference Routing for Cost-Efficient Document Field Extraction
arXiv:2608.06607v1 Announce Type: new Abstract: Most document-extraction systems use a single model for all documents. This is simple but can be costly for easy cases and…
FinanceHarness: Autonomous Financial Deep Research Framework
arXiv:2607.27853v2 Announce Type: replace Abstract: Powered by advances in LLMs and autonomous agents, deep research has become one of the most widely adopted agentic products. However,…
Beyond "AI Language": The case for the idiolectal nature of LLM output
arXiv:2608.06589v1 Announce Type: new Abstract: While large language model outputs are frequently analysed as a collective super variety termed "AI language," this chapter argues that this…
A Practical Evaluation Method for Long-Form Simultaneous Speech-to-Speech Translation
arXiv:2606.15059v2 Announce Type: replace Abstract: Simultaneous speech-to-speech translation (SimulS2ST) enables real-time cross-lingual communication, but existing evaluation has focused largely on short or pre-segmented speech rather than…
TradeVerse: A Longitudinal Benchmark of Political Negotiation in International Trade
arXiv:2608.06549v1 Announce Type: new Abstract: LLMs are increasingly being applied to tasks involving institutional and political texts, but existing benchmarks evaluate them on isolated documents or…
How Long Reasoning Chains Influence LLMs' Judgment of Answer Factuality
arXiv:2604.06756v2 Announce Type: replace Abstract: Large language models (LLMs) has been widely adopted as a scalable surrogate for human evaluation, yet such judges remain imperfect and…
Don't `Well, Actually' Me Unless You Know What You're Talking About: Weak Presupposition Verification Degrades General QA Performance
arXiv:2608.06539v1 Announce Type: new Abstract: False-presupposition QA (FPQA) tests LLMs on their ability to identify false presuppositions in questions and abstain or correct them rather than…
SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent
arXiv:2608.07449v1 Announce Type: cross Abstract: LLM agents increasingly adapt to recurring tasks by accumulating procedural knowledge in skills. These skills are lightweight, reusable textual artifacts that…
Confidence Estimation for Financial Vision-Language Models in Chart and Document Understanding
arXiv:2608.06532v1 Announce Type: new Abstract: LVLMs are increasingly used to read financial charts, tables, and documents, where a single misread figure can move a decision and…