Mini toolsPapers
Filter by company
-
Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution
-
GISA: A Benchmark for General Information-Seeking Assistant
-
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse TasksAmazon / Boston University, Carnegie Mellon University, Columbia University, Dartmouth College, Duke University, Michigan State University, Princeton University, Stanford University, The Ohio State University, University of California, University of Oxford, University of Southern California, University of Texas
-
GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning
-
Think like a Scientist: Physics-guided LLM Agent for Equation DiscoveryUniversity of California
-
Intelligent AI Delegation
-
AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection
-
HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model
-
LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts
-
Abstractive Red-Teaming of Language Model Character
-
Kelix Technical Report
-
DSO: Direct Steering Optimization for Bias Mitigation
-
LLM-in-Sandbox Elicits General Agentic Intelligence
-
Visual Foresight for Robotic Stow: A Diffusion-Based World Model from Sparse Snapshots
-
On-Policy Context Distillation for Language Models
-
Iterative Reranking as a Compute-Scaling Method for LLM-based Rankers
-
KG-CRAFT: Knowledge graph-based contrastive reasoning with LLMs for enhancing automated fact-checking
-
Pattern Discovery with Wide-Lens Analysis and Sharp-Focus Validation
-
ChatLLM network: More brains, more intelligenceBeijing Institute of Technology
-
RISE: Self-Improving Robot Policy with Compositional World Model
-
CODE-SHARP: Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs
-
Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives
-
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
-
SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices
-
BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation
-
Voxtral Realtime
-
Accelerating Mathematical and Scientific Discovery with Gemini Deep Think
-
OmniSapiens: A Foundation Model for Social Behavior Processing via HARPOMassachusetts Institute of Technology, Nanyang Technological University, National University of Singapore, Qatar Computing Research Institute, University of Rochester
-
GameDevBench Evaluating Agentic Capabilities Through Game Development Wayne Chi1 , Yixiong Fang1 , Arnav Yayavaram1 , Siddharth Yayavaram1 , Seth Karten2Carnegie Mellon University, Princeton University
-
ArtifactLens: Hundreds of Labels Are Enough for Artifact Detection with VLMs
-
EchoJEPA: A Latent Predictive Foundation Model for EchocardiographyCohere / University Health Network, University of California, University of Toronto, Vector Institute
-
Federated Balanced Learning
-
MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE
-
CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning
-
Autoregressive Image Generation with Masked Bit Modeling
-
iGRPO: Self-Feedback–Driven LLM Reasonin
-
ML-DCN: Masked Low-Rank Deep Crossing Network Towards Scalable Ads Click-through Rate Prediction at Pinterest
-
Agentic LLMs as Powerful Deanonymizers: Re-identification of Participants in the Anthropic Interviewer Dataset
-
HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing
-
VirtualEnv: A Platform for Embodied AI Research
-
Intelligence ExplosionMachine Intelligence Research Institute
-
Prompt Reinjection: Alleviating Prompt Forgetting in Multimodal Diffusion Transformers
-
DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving
-
ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training
-
CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMsMeituan / Nanjing University, National University of Singapore, Shanghai Jiao Tong University, Zhejiang University
-
CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation
-
DreamDojo: A Generalist Robot World Model from Large-Scale Human VideosNVIDIA / Hong Kong University of Science and Technology, Korea Advanced Institute of Science & Technology, Stanford University, University of California, University of Toronto, University of Washington
-
Can Post-Training Transform LLMs into Causal Reasoners?Fudan University, Shanghai Artificial Intelligence Laboratory
-
Learning a Generative Meta-Model of LLM ActivationsUC Berkeley
-
Self-Consistency Improves Chain of Thought Reasoning in Language Models
