Papers
Videos
Whiteboards
Open Problems
Pricing
Log in
Sign up
Papers
Whiteboards
Videos
Open Problems
Pricing
Log in
Sign up
Whiteboard Explanations
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
Hierarchical Concept Geometry in Language Models
LeJEPA: Conditions for World Model Identifiability
Sleep-Like Memory Consolidation in LLMs
SkillOpt: Self-Evolving Agent Skills
Self-Policy Distillation via Capability Projection
ActiveGraph: Log-Primary Agentic Systems
AI-Driven Formal Proof Search in Mathematics
Gated DeltaNet-2: Decoupled Gates in Linear Attention
Curiosity in 3D: Episodic Context & Persistent Worlds
Equilibrium Reasoners: Scalable Attractor Dynamics
Minimal RLVR Training with Rank-1 Trajectories
CODA: Transformer Blocks as GEMM-Epilogue Programs
HRM-Text: Efficient Hierarchical Recurrent Pretraining
General Preference Reinforcement Learning
Explicit Lower Bounds in the Unit Distance Problem
Generative Recursive Reasoning Models
Universal API for Text Optimization
Mathematical Insights on Loss of Plasticity in DNNs
UT Memory: Depth-State Trade-offs in Reasoning
ClawNet: Cross-User Governance for Autonomous Agents
Federated Attentive Message Passing (FedAMP)
Scientific Theory of Deep Learning
Decoupled DiLoCo: Resilient Distributed Pre-training
Hyperloop Transformers: Efficient Language Modeling
Soft-Label Governance in Multi-Agent Systems
Adversarial Multi-Agent LLM Defect Review
Scaling Self-Play with Self-Guidance
Convergent Evolution: LM Number Representations
Generalization at the Edge of Stability
Agentic Forecasting with Bayesian Linguistic Beliefs
AI Agents Lack Scientific Reasoning
Cluster-Aware Upcycling for MoE Specialization
AVA: Curated Generative AI for Policy Research
Neural Garbage Collection: Efficient LM Memory Management
VLA Foundry: Unified Vision-Language-Action Training
Scaling Test-Time Compute for Agentic Coding
Show More
