SkillNet: Create, Evaluate, and Connect AI Skills Paper • 2603.04448 • Published 21 days ago • 87 • 6
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders Paper • 2603.06569 • Published 13 days ago • 112 • 5
WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching Paper • 2603.06331 • Published 13 days ago • 3 • 3
$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space Paper • 2603.04948 • Published 14 days ago • 1 • 3
DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces Paper • 2603.05607 • Published 14 days ago • 3 • 3
Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation Paper • 2602.05827 • Published Feb 5 • 17 • 3
DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation Paper • 2602.12160 • Published Feb 12 • 38 • 5
Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks Paper • 2602.14689 • Published Feb 16 • 1 • 3
Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens Paper • 2602.13517 • Published Feb 13 • 2 • 2
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs Paper • 2603.05890 • Published 14 days ago • 89 • 5
Real Money, Fake Models: Deceptive Model Claims in Shadow APIs Paper • 2603.01919 • Published 17 days ago • 2 • 1
Believe Your Model: Distribution-Guided Confidence Calibration Paper • 2603.03872 • Published 15 days ago • 39 • 4
How Far Can Unsupervised RLVR Scale LLM Training? Paper • 2603.08660 • Published 10 days ago • 56 • 4
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion Paper • 2603.06577 • Published 13 days ago • 48 • 6
MOVA: Towards Scalable and Synchronized Video-Audio Generation Paper • 2602.08794 • Published Feb 9 • 156 • 5
QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining Paper • 2602.07085 • Published Feb 6 • 189 • 3
UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction Paper • 2512.12941 • Published Dec 15, 2025 • 2 • 2
Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs Paper • 2602.07276 • Published Feb 7 • 11 • 3
SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers Paper • 2602.05115 • Published Feb 4 • 18 • 10