FVSpec: Real-World Property-Based Tests as Lean Challenges Paper • 2606.01008 • Published 17 days ago • 3
DreamX-World 1.0: A General-Purpose Interactive World Model Paper • 2606.16993 • Published 2 days ago • 89 • 7
Statistically Reliable LLM-Based Ranking Evaluation via Prediction-Powered Inference Paper • 2606.05308 • Published 14 days ago • 1 • 3
Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics Paper • 2606.12476 • Published 7 days ago • 3
Squeeze-Release: Iterative Pruning with Exact Structural Minimization Paper • 2606.14346 • Published 5 days ago • 4
Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving Paper • 2606.06302 • Published 2 days ago • 9 • 3
Memento: Reconstruct to Remember for Consistent Long Video Generation Paper • 2606.14667 • Published 5 days ago • 12 • 4
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data Paper • 2606.13432 • Published 6 days ago • 96 • 5
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling Paper • 2606.13473 • Published 6 days ago • 88 • 2
Rethinking RAG in Long Videos: What to Retrieve and How to Use It? Paper • 2606.13141 • Published 6 days ago • 32 • 3
AdaSR: Adaptive Streaming Reasoning with Hierarchical Relative Policy Optimization Paper • 2606.14694 • Published 5 days ago • 1 • 3
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers Paper • 2606.13289 • Published 6 days ago • 28 • 3
WebChallenger: A Reliable and Efficient Generalist Web Agent Paper • 2606.10423 • Published 8 days ago • 2 • 4
A Stationary (and Therefore Compatible) Representation is All You Need Paper • 2606.12488 • Published 7 days ago • 1 • 3
From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion Paper • 2606.12303 • Published 7 days ago • 32 • 3
On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance Paper • 2606.00467 • Published 18 days ago • 1 • 4