Papers
Videos
Whiteboards
Open Problems
Pricing
Log in
Sign up
Papers
Whiteboards
Videos
Open Problems
Pricing
Log in
Sign up
Whiteboard Explanations
Decoupling Weight Magnitude and Direction
Autodata: Agentic Synthetic Data Framework
Efficient LLM Evaluation with BENCHPRESS
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
S-Agent: Evidence-Driven Spatial Reasoning
Cognitive Models in Persuasion Games
EgoInfinity: 4D Hand-Object Data Engine
SC3-Eval: Video Evaluation for Robot Policies
DO AS I DO: Scalable Dexterous Manipulation Data
Neurrator: Semantic Decoding of Visual Cortex
Dynamic 3D Reconstruction: Disentangled Ego-Motion
Adversarial Robustness of Fable 5 & Opus 4.8
Safe GPU Programming with cuTile Rust
Universal Image Restoration via CoT Reasoning
Looped World Models: Efficient Iterative Simulation
Fixed-Point Reasoners
Temporal Difference Visual Representation Learning
HUG: Learning Dexterous Robotic Grasping
Google's TPU Evolution: From v2 to Ironwood
AI Out-Persuades Expert Humans
VibeThinker-3B: Compact Verifiable Reasoning
Universal Manipulation Exoskeleton for Compliant Robotics
Rubric-Guided Self-Distillation for LLMs
Modality Forcing for Joint Image-Depth Generation
From AGI to ASI: Pathways and Challenges
MaxProof: Scaling Mathematical Proofs with RL
MiniMax Sparse Attention for Ultra-Long Context LLMs
CHORUS: Decentralized Multi-Robot VLA Collaboration
Brain-Guided LLMs for Robust Deductive Reasoning
Post-Training Interpretability in LLMs
Autonomous Research via Hypothesis-Tree Refinement
FACTR 2: Force Sensing for Commodity Robot Arms
Evidence Markets: Aggregating Beliefs & Evidence
Decentralized Multi-Agent Systems with Shared Context
Dignity Stack: Commons-Governed AI Architecture
Flow-DPPO: KL-Constrained RL for Flow Matching
TimpaTeks: In-place Diffusion Text Editing
UniSHARP: Universal Monocular View Synthesis
Fast Transients in Archival Plates
MilliVid: Hierarchical Consistency in Video Generation
AI Agents Transform Knowledge Work
Deep Representation Learning Theory
Stochastic Equilibrium: Convergence in DSGE Models
Trajectory Dynamics in Language Models
AI Refuting Economic Theory: Empirical Evidence
Leipzig Benchmark for Mathematical LLM Evaluation
Latent Reasoning with Normalizing Flows
Proof of Scaling-Exponent Identity at Jamming
AlloGen: Conformation-Selective Binder Design
Agentic AI: Self-Revising Discovery
Space-Based GNSS Interference Detection
Pretraining RNNs without Recurrence
QKV Projection Sharing in Transformers
GRAIL: Virtual Humanoid Loco-Manipulation
Crazyflow: GPU-Accelerated Drone Simulator
Hyper-Epoch Pretraining with q0
Self-Distilled Policy Gradient
LEAP: Agentic LLMs for Formal Mathematics
Mixture-Density Model for Depth and Flying-Point Elimination
LLMs Need Sleep: Memory & Self-Modification
KVarN: Variance-Normalized KV-Cache Quantization
Stable-Layers: RL Fine-Tuning for Decomposition
Strong Stochastic Flow Maps for Neural SDEs
Stateful Monitoring for Distributed Attacks
Optimized ECDLP Point Addition Circuits
NeuROK: Generative 4D Object Kinematics
Mellum 2: A 12B MoE Model for Software Engineering
Vision-Language Models: Suppressing Female Bias
mRNAutilus: Multi-Objective mRNA Design
Physicist-Supervised AI in Scientific Software
Training Ecosystems: Emergent Learning in Ecology
Adopt ≠ Adapt: LLM Behavior in the Wild
GPIC: Permissive Image Corpus for Generation
Learn from Latents: Sample Complexity Theory
Qwen-VLA: Unified Vision-Language-Action Model
Emergent Perceptual Geometry in LLMs
SIA: Self-Improving AI via Harness & Weight Updates
Disproof of the Sum-Product Conjecture in Reals
Self-Improving LMs with Bidirectional Evolutionary Search
Simulating Human Memory with LLMs
Forgetting in LMs: Capacity, Optimization & Replay
Unified Neural Scaling Laws
Atomically Precise Carbon Mechanosynthesis on H:Si(100)
Epicure: Food Ingredient Embedding Geometry
R^3: 3D Reconstruction via Relative Regression
Show More
