O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning Paper • 2607.18142 • Published 8 days ago • 8 • 2
Multimodal Speaker Verification as a Threat to Speaker Anonymization Paper • 2607.19636 • Published 6 days ago • 1 • 2
Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning Paper • 2607.21653 • Published 6 days ago • 27 • 1
LAMAR: An Open Language-Aware Multilingual Alignment Reranker Paper • 2607.22042 • Published 4 days ago • 9 • 1
SceneActBench: Can Agents Act on the 3D Scenes They See? Paper • 2607.22393 • Published 4 days ago • 4 • 1
IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation Paper • 2607.22375 • Published 4 days ago • 5 • 2
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems Paper • 2607.21503 • Published 5 days ago • 19 • 4
Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making Paper • 2607.14277 • Published 13 days ago • 6 • 2
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Paper • 2607.22529 • Published 4 days ago • 31 • 1
VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression Paper • 2607.12756 • Published 14 days ago • 2 • 3
Spectral Prior for Reducing Exposure Bias in Diffusion Models Paper • 2607.22091 • Published 4 days ago • 3 • 2
Scaling Native Multimodal Pre-Training From Scratch Paper • 2607.22043 • Published 4 days ago • 20 • 1
Interactive Training 2: Auditable Control Plane for Live Model Training Paper • 2607.18314 • Published 11 days ago • 16 • 2
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators Paper • 2607.20465 • Published May 19 • 48 • 2
ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders Paper • 2607.21217 • Published 5 days ago • 6 • 2
Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation Paper • 2607.21485 • Published 5 days ago • 8 • 2