The AI Wire

178 articles tagged "cs-CV" — page 6 of 6

Solving Spatial Supersensing Without Spatial Supersensing [TOP LAB](arxiv.org)

2025-11-23|paper|arXiv

<think>

cs-CV cs-LG

EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards (arxiv.org)

2025-11-21|paper|arXiv

<think>

cs-CV

Solving Spatial Supersensing Without Spatial Supersensing [TOP LAB](arxiv.org)

2025-11-21|paper|arXiv

<think>

cs-CV cs-LG

Dataset Distillation for Pre-Trained Self-Supervised Vision Models (arxiv.org)

2025-11-21|paper|arXiv

<think>

cs-CV cs-AI cs-LG

NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses (arxiv.org)

2025-11-21|paper|arXiv

<think>

cs-CV

GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization (arxiv.org)

2025-11-20|paper|arXiv

<think>

cs-CV

In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data (arxiv.org)

2025-11-20|paper|arXiv

<think>

cs-RO cs-AI cs-CV

Think Visually, Reason Textually: Vision-Language Synergy in ARC (arxiv.org)

2025-11-20|paper|arXiv

<think>

cs-CV cs-AI cs-CL

GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI [TOP LAB](arxiv.org)

2025-11-20|paper|arXiv

<think>

cs-CV cs-AI

RoMa v2: Harder Better Faster Denser Feature Matching (arxiv.org)

2025-11-20|paper|arXiv

<think>

cs-CV

ARC Is a Vision Problem!(arxiv.org)

2025-11-19|paper|arXiv

<think>

cs-CV cs-AI cs-LG

UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning (arxiv.org)

2025-11-19|paper|arXiv

<think>

cs-CV

Segment Anything Across Shots: A Method and Benchmark (arxiv.org)

2025-11-18|paper|arXiv

<think>

cs-CV

OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation [TOP LAB](arxiv.org)

2025-11-18|paper|arXiv

<think>

cs-CV cs-LG

Alpha Divergence Losses for Biometric Verification [TOP LAB](arxiv.org)

2025-11-18|paper|arXiv

<think>

cs-CV cs-AI

Scaling Spatial Intelligence with Multimodal Foundation Models (arxiv.org)

2025-11-18|paper|arXiv

<think>

cs-CV cs-AI cs-LG

Back to Basics: Let Denoising Generative Models Denoise (arxiv.org)

2025-11-18|paper|arXiv

<think>

cs-CV

Synergy vs. Noise: Performance-Guided Multimodal Fusion For Biochemical Recurrence-Free Survival in Prostate Cancer [TOP LAB](arxiv.org)

2025-11-17|paper|arXiv

<think>

q-bio-QM cs-CV cs-LG

Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling (arxiv.org)

2025-11-16|paper|arXiv

<think>

cs-CV

Depth Anything 3: Recovering the Visual Space from Any Views (arxiv.org)

2025-11-16|paper|arXiv

<think>

cs-CV

Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals [TOP LAB](arxiv.org)

2025-11-16|paper|arXiv

<think>

cs-CV cs-CL

Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis [TOP LAB](arxiv.org)

2025-11-11|paper|arXiv

<think>

cs-LG cs-CV

GentleHumanoid: Learning Upper-body Compliance for Contact-rich Human and Object Interaction (arxiv.org)

2025-11-09|paper|arXiv

<think>

cs-RO cs-CV cs-HC

Learning from Single Timestamps: Complexity Estimation in Laparoscopic Cholecystectomy [TOP LAB](arxiv.org)

2025-11-09|paper|arXiv

<think>

cs-CV

GentleHumanoid: Learning Upper-body Compliance for Contact-rich Human and Object Interaction (arxiv.org)

2025-11-08|paper|arXiv

<think>

cs-RO cs-CV cs-HC

Learning from Single Timestamps: Complexity Estimation in Laparoscopic Cholecystectomy [TOP LAB](arxiv.org)

2025-11-08|paper|arXiv

<think>

cs-CV

GentleHumanoid: Learning Upper-body Compliance for Contact-rich Human and Object Interaction (arxiv.org)

2025-11-07|paper|arXiv

<think>

cs-RO cs-CV cs-HC

Learning from Single Timestamps: Complexity Estimation in Laparoscopic Cholecystectomy [TOP LAB](arxiv.org)

2025-11-07|paper|arXiv

<think>

cs-CV

← Prev6 / 6