Command Palette
Search for a command to run...
Papers
Daily updated cutting-edge AI research papers to help you keep up with the latest AI trends
papers

InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter

OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs






























Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
Let’s Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts
AVO: Agentic Variation Operators for Autonomous Evolutionary Search
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use
WITHEVERYONE: UNIFIED PLANNING AND IDENTITY GROUNDING FOR GROUP IMAGE GENERATION
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?
4DAnyone: Create Anyone in 4D from a Casual Monocular Video
FACET: PRESERVING SOURCE INTENT AND EXECUTABLE STATE IN TERMINAL TASK SYNTHESIS
EnvHarness: Awakening Static Worlds for Agent Learning
SCALING PROPERTIES OF TEXT CONDITIONING IN VISUAL GENERATION
DifusionGemma Technical Report
CHARTGALAXY: A DATASET FOR INFOGRAPHIC CHART UNDERSTANDING AND GENERATION
A MODULAR ZERO-SHOT PIPELINE FOR ACCIDENT DETECTION,LOCALIZATION, AND CLASSIFICATION IN TRAFFICSURVEILLANCE VIDEO
SPADE ♠: Self-Play in Adaptive Synthetic Executable Environments
Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation
Zetta: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation
Agentopia: Long-Term Life Simulation and Learning in Agent Societies
MARCH: Scaling Recurrent Memory with Content-Routed State Anchors
GAN-BERT: Generative Adversarial Learning for Robust Text Classification with a Bunch of Labeled Examples
Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency
AVA-Encoder: Towards Agent-Native Video Representation Learning
Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
ASI-BENCH: AT THE DAWN OF ARTIFICIAL SUPERINTELLIGENCE
Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Memory Requirements
Demystifying Agent Skills: Why They Work—Until They Don’t
Open Mathematical Problems as an AI Reasoning Benchmark