Papers
Videos
Whiteboards
Open Problems
Pricing
Log in
Sign up
Papers
Whiteboards
Videos
Open Problems
Pricing
Log in
Sign up
Whiteboard Explanations
LLM Belief Coevolution: Generalists & Specialists
MatrAIx: 8.3B Persona Agents for AI Testing
Physics of Multimodal Pretraining
0/1-Polytopes with Exponentially Small Edge Expansion
Policy-Graded Evaluation of Coding Agents
Counterexample to Period-Index Conjecture
Hunyuan3D-Buffalo 1.0: Unified Multimodal 3D Model
Ego2Robot: Scalable Robot Data Synthesis
LLM Code Editing: Deletion Avoidance Mitigation
Shieldstral: Adaptive Multimodal Moderation
LLMs Fail at Tabular Prediction: A Dimensional Challenge
Counterexamples to Landis Conjecture (n ≥ 3)
PTP: LLM Inversion via Prev-Token Prediction
InfiniSplat: Implicit Gaussian Decoding
TEngineDB-V: OLAP-Native Vector Search
Zero-Mem: Token-Free LLM Memory
Socratic Test: Dynamic Multimodal Assessment
Prompt Graph Engineering: Four Conditions
Racing to Ruin: R&D Competition Risks
LLM Consciousness: Restoring Human Beliefs and Values
Chimera: Hybrid Visual Diffusion Transformers
Causal Dynamics in Pre-Replicator Systems
HumanCLAW: VLMs and Embodied Action
Warp Divergence in NVIDIA GPUs: Pascal to Blackwell
Explorative Modeling: Third Pretraining Axis
Frontis-MA1: AI4AI Model for Self-Improved ML
Refutation of Maxwell Conjecture: 5-Charge Case
HANDBOOK.md: Long-Context Policy Benchmark
Parallel Decoding Distillation for Image & Video Generation
Bridging Compute- and Data-Optimal Pretraining
Speech Cues Enhance LLMs in Speed Dating Prediction
Werner Two-Copy Distillability & Trace Inequality
Continual Learning from Deployment Feedback
Sedimentation and Rebound in Dusty Plasma Crystals
Reading Mathematics: A Study Guide
Kimi K3: Open Frontier Intelligence
Sharp Deviation Bounds for Nonnegative Sums
LLMs and Evolving User Intent
Graph-Based Agentic AI with LangGraph
Analytic Solution to 2-Copy Distillability of Werner States
Authority Framing in CI/CD Pipelines
GenAI, Grades & Student Satisfaction in Higher Ed
Standard Model via Division Algebra Embeddings
AREX: Recursive Self-Improving Research Agent
AXIS: Community Data Engine for Robot Manipulation
HOPE: Hilbert Operator Progressive Encoding
PoTRE: Cognitive Heterogeneity in Test-Time Reasoning
Environment-Free Synthetic Data for API Agents
CriPO: Enhancing Rubric-based RL
LLM-as-a-Coach: Learning for Non-Verifiable Tasks
ModPack: An Extensible Teleoperation Interface for Bimanual Mobile Manipulation
Counter-Example to Batyrev's Conjecture
LLM Fortunetelling in China: Practices & Impacts
Loop the Loopies: Effective Layer-Loop Recurrence
Masked Visual Actions for Unified World Modeling
AI Value Alignment & Evolving Social Norms
EvolvingWorld: Co-Evolving Literary Agents & Worlds
Reinforcement Learning: Algorithms & Foundation Models
Quantum ECDLP: Space-Efficient Point Addition
Non-vacuous Bounds for RLVR in Billion-Parameter LLMs
Near Speed-of-Light GPU Collectives
Pretraining and RL Scaling in Reasoning
T²MLR: Transformer with Temporal Recurrence
The Severance Problem in Personalized LLM Assistants
Qubes OS Security: Longitudinal Analysis
In-Place Tokenizer Expansion for LLMs
DeepLoop: Loop-Aware Scaling for Transformers
Value Leakage: Covert Bias in LLMs
2026 Falcon 9 Lunar Impact Modeling
SeeSE3: 3D Space in Vision Models
Gravity Signatures in Holographic Quantum Codes
Self-Correcting CMJP for Joint Image & Text Generation
Mechanistic World Models and Autonomous Discovery
Harness Evolution for LLM Agents
LLMs' Deep Comprehension in Computer Architecture
TRACE: Turn-Level Reward in RL
Self-Improving Agentic Systems Survey
Religion & AI as Distributed Meaning Systems
Seriality Gap in Video Diffusion Models
Mathematics of Data Science
Prediction Flips in LLMs: Beyond Aggregate Accuracy
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
Predictive, Aligned Robot Learning via Lumo-2
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
Show More
