Paper abstract and links
The authors’ abstract, vote count and code link of any paper on the current daily list.
On the current list
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels
- Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation
- Deep Search in Real-World Web Environments
- Editing Images into Reusable Layers via Compositional Edit-Prior Distillation
- IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
- Toward Recursive Self-Improvement in Physical AI
- Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models
- What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models
- LaLa-World: Scaling Latent World Models with Natural Language Actions
- FilmFlow: Agentic System for 3D Virtual Film Cinematography
- Self-Distilling Future Video Representations for World Action Models
- Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE
- Policy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative Tasks
- Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents
- Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V
- Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports
- Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
- RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing
- RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting
- Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
- Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation
- RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation
- Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos
- Rethinking Sequence Compression with Test-time Regression
- AgentVQA: A Unified Benchmark for Agentic Visual Understanding
- AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark
- MolLean: A Process-Verifiable Language for Chemical Reasoning
- RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention
- Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models
- Reading, Writing, Sharing, and Interacting with the World through Video