Papers Videos Whiteboards Open Problems Pricing Log in Sign up

Papers Whiteboards Videos Open Problems Pricing Log in Sign up

Generate videos that make complex ideas click

Sign Up to Generate Custom Videos

Subscribe on YouTube

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

Belief Coevolution in a Social Network of Generalist and Specialist Large Language Models

Hunyuan3D-Buffalo 1.0: A Unified 3D Model That Understands, Creates, and Edits

InfiniSplat: Surface-Aligned 3D Gaussians from a Single Image

Permission Denied: How Security Policies Break Coding Agents

PTP: Inverting Language Models by Learning to Predict Backwards

To Add Is Machine, To Delete Is Human

TEngineDB-V: OLAP-Native Vector Search for Large-k Workloads at Tencent

What Makes Prompts a Graph: Four Conditions That Define Prompt Engineering's Next Evolution

Explorative Modeling: A Third Axis for Generative AI

When Safety Training Suppresses a Model's Soul

A Type Theory of Sense: Witnessed Choice in Stratified Semantic Spaces

Open Horn Type Theory: Formalizing Structured Failure

The Maxwell Conjecture is False

HumanCLAW: Can Vision-Language Models Act Through a Body?

HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following

Counting Corners to Classify Knotted Tori in Five Dimensions

Proving Bound Entanglement: A New Inequality Settles Werner State Distillability

Learning on the Job: Continual Learning from Deployment Feedback for Frozen-Weights Agents

How to Read Mathematics? A Study Guide

Sharp Bounds for Sums of Random Variables: Resolving the Feige Conjecture

When Plasma Crystals Fall: Gravity, Yukawa Forces, and the Physics of Rebound

When Knots Break the Rules: Non-Orientable Lagrangian Fillings

Beyond Thurston-Bennequin: New Invariants for Legendrian Surfaces

Lagrangian Fillable Legendrian Knots

Strongly Invertible Legendrian Knots

Dream to Control: Learning Behaviors by Latent Imagination

Graph-Based Agentic AI with LangGraph: Structured Orchestration for Stateful Business Workflows

LLMs Get Lost In Multi-Turn Conversation

Masked Visual Actions for Unified World Modeling

The Two-Copy Threshold: Solving Werner State Distillability

VLM-Loc: Teaching Robots to Find Themselves Through Language

Beyond 3D VQAs: Teaching Vision-Language Models to See in Three Dimensions

PoTRE: Smarter Reasoning Through Cognitive Diversity

HOPE: Decoding Deep Networks Through Functional Geometry

When Trusted Pipelines Become Attack Vectors

From Game Theory to Foundation Models: The Evolution of Reinforcement Learning

EvolvingWorld: Characters and Worlds That Grow Together

When Stringy Hodge Numbers Break: A Counter-Example to Batyrev's Conjecture

Every Microsecond Matters: Reaching Near Speed-of-Light GPU Communication

Rethinking the Evaluation of Harness Evolution for Agents

The Severance Problem: LLMs are Unaware of the Person Beyond the Prompt

TRACE: Dense Credit Assignment for Long-Horizon AI Agents

Understanding Reasoning from Pretraining to Post-Training

Watching a Rocket Stage Crash Into the Moon

T²MLR: Temporal Middle-Layer Recurrence for Reasoning

Quantum Gravity Signatures in Holographic Codes

From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery

Ring-Zero: Trillion-Scale Reinforcement Learning for Emergent Reasoning

The Seriality Gap in Video Diffusion Models

Chrome Extension