Papers
Videos
Whiteboards
Open Problems
Pricing
Log in
Sign up
Papers
Whiteboards
Videos
Open Problems
Pricing
Log in
Sign up
Whiteboard Explanations
Religion & AI as Distributed Meaning Systems
Mathematics of Data Science
B-spline Policy: Accelerated Robotic Manipulation
Ring-Zero: Trillion-Parameter Zero RL Reasoning
Requential Coding: Efficient Model Compression
Mixture of Frames Policy for Bimanual Manipulation
CLAP: Direct VLM-to-VLA Adaptation
Convex Optimization Lecture Notes
Architectural Wisdom in AI Optimization
GPU-Tile-Sim: LLM GPU Co-Design Simulator
Towards Predictive, Aligned, and Scalable Robot Learning
GenCeption: Video Generation for Unified Vision
FlowDAgger: Latent-Space Human Adaptation
Sovereign Open-Source Bilingual LLM
Human-AI Interaction in Structural Design
Automation Without Understanding: AI & Math
Adversarial Psychometrics: Measuring Beyond Human Scale
User Identity and Moral Judgments in LLMs
UnfoldArt: Zero-Shot 3D Articulated Recovery
KAT-Coder-V2.5: Advances in Agentic Code Engineering
Lecture Notes on RMT: Results & Analytical Tools
Social Norms in Dynamic Human-AI Coordination
Billions of Sketches Reveal Cultural Concept Variation
Trees from Marginals: Factorized Autoregressive Decoding
Single-Rollout Async Optimization in Agentic RL
ProxyPose: 6-DoF Pose Tracking via Video Diffusion
Hybrid Collective Cognition: Network Synthesis
RoboDojo: Unified Benchmark for Manipulation
Wan-Streamer v0.2: High-Res, Low-Latency AV Streaming
Faithfulness of the 4-Strand Burau Representation
SiamJEPA: Siamese Encoders in JEPA
Statistical Analysis of AMS Fireball Reports
GaP: Graph-as-Policy for Multi-Agent Robotics
Deform360: Multi-view Dataset for Deformable Robotics
LLM-as-a-Verifier: Probabilistic Verification
Gemma 4: Multimodal Transformer Report
Decomposer: MIDI-to-Strudel Decompilation
OmniTacTune: Tactile Residual RL for Visual Policies
Vision Pretraining for Dense Spatial Perception
Adoption Impact of CLI AI Coding Agents
Kani: A Model Checker for Rust
AI-Native Games: Taxonomy & Roadmap
NeuroCogMap: Cognitive Organization of LLMs
2048-Spin BAW Ising Machine for NP Problems
Mathematical Intro to Diffusion Models
LM Training with Verifiable Rewards & Human Demos
Unified Scaling Law for LLM Training
WARP: Recovering Training Data Portfolios
Program-as-Weights for Fuzzy Functions
Single-Layer RL Adaptation in Transformers
LeVLJEPA: Non-Contrastive Vision-Language Pretraining
Self-Evolving Agentic RL Systems
HABIT: Human-Aware Robot Manipulation
Clinical AI Evaluation: Real-POC Insights
Structured 4D Latent Model for Robot Planning
Symbolic Communication for Efficient Multi-Agent Reasoning
Latent Actions via Factorized Transitions
Hierarchical Global Attention in Transformers
AdaJEPA: Adaptive Latent World Model
MOPD: Multi-Teacher Distillation in LLM Post-Training
GPC: Generative Pretraining for Motor Control
SWE-Together: Interactive Coding Agent Benchmark
Orca: Unified World Latent Modeling
35B Agent: Horizon Scaling for Trillion-Level Performance
TheoremGraph: Unifying Formal & Informal Math
Interval-Aware RL with Predictive Temporal Structure
SimFoundry: Modular Scene Generation for Policy Learning
Agentic AI: Insights from Codex Usage
BinEval: Binary Questions for LLM Evaluation
Extracting Neural Materials from Multi-view Images
Red Queen Gödel Machine: Co-Evolving Agents
Verification Horizon: Coding Agent Reward Limits
Agentic AI: Foundations to Scalable Systems
Probabilistic Computer with 1M p-bits
VibeAct: Vibrotactile Sensing for Dexterous Manipulation
Language Digital Twins for Elderly Assistance
EmuGEMM: Fused Tensor Kernels for Matrix Emulation
MJEPA: Scalable Joint-Embedding for AV Learning
Emergent Capabilities in Transformers
Decoupling Weight Magnitude and Direction
Autodata: Agentic Synthetic Data Framework
SPIRAL: RL for Search and Aggregation
Efficient LLM Evaluation with BENCHPRESS
SkyJEPA: Latent World Models for Quadrotors
OpenThoughts-Agent: Data Recipes for Agentic Models
FLAT: Feedforward Triangle Splatting for 3D Scene Generation
Qwen-AgentWorld: Unified Language World Models
Inverting the Bellman Equation: World Model Extraction
Equilibrium World Models
Tapered Language Models: Depth-Aware Optimization
Unlimited OCR: Efficient Long-Horizon Parsing
VideoAgent: Unified Framework for Video Editing
CalTennis: Multi-View Tennis Pose Benchmark
Thinking in Boxes: 3D Editing for Real Images
Thermodynamic Measure of Intelligence
LLMs Beyond Readable Language: BabelTele
FAPO: Autonomous LLM Pipeline Optimization
LOCUS: U.S. Local Ordinance Corpus
Data Centers and U.S. Electricity Rates
VIMPO: Implicit Value Optimization in LLMs
Show More
