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

CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification

Rubric-Guided Self-Distillation: Post-Training Without Verifier Overhead

FACTR 2: Teaching Cheap Robots to Feel Without Force Sensors

From AGI to ASI: Pathways, Bottlenecks, and the Limits of Machine Intelligence

MiniMax Sparse Attention: Orders-of-Magnitude Speedups for Ultra-Long Context LLMs

MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation

Decentralized Multi-Agent Systems with Shared Context

Seeing the Unseen: How Optical Flaws Reveal Real Transients in Century-Old Sky Photos

D-VAL: Proving Planning Domains Do the Same Thing

Can AI Refute Economic Theory? Testing Models on Hidden Errors

How AI Agents Reshape Knowledge Work: Autonomy, Efficiency, and Scope

Pretraining Recurrent Networks without Recurrence

A Mathematical Theory of Memory: Unifying Deep Learning Through Compression

When Equilibria Converge: The Mathematics Behind DSGE Stability

PDDLStream: When Planners Meet Samplers

Proving the Hidden Identity in Jamming Criticality

Do Transformers Really Need Three Projections?

Chasing Lightning: Unmasking a Space-Based GNSS Jammer

Bidirectional Reasoning Flow

Flying-Point-Free Depth: A Mixture-Density Solution to Ambiguity

KVarN: Taming Quantization Errors in Long-Context Reasoning

Self-Distilled Policy Gradient: Dense Supervision for Smarter Language Models

GPIC: The First Giant Permissive Image Corpus for Visual AI

Breaking Bitcoin's Curve: Quantum Circuits for Elliptic Curve Cryptanalysis

Self-Improving Language Models with Bidirectional Evolutionary Search

Mellum 2: A 12B MoE Model That Codes Like a Frontier System on a Single GPU

Qwen-VLA: One Model to Control Them All

Learn from Your Own Latents: Why Predicting Internal Representations Beats Predicting Tokens

Training Ecosystems: When Predator-Prey Models Learn to Count

SIA: Self-Improving AI with Harness & Weight Updates

The Sum-Product Conjecture is False for Real Numbers

Learning Without Forgetting: The Self-Replay Solution

Language Models Need Sleep

Epicure: Navigating the Emergent Geometry of Food Ingredient Embeddings

Building Molecules Atom by Atom with Mechanical Force

Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning

SkillOpt: Teaching Agents to Evolve Their Own Expertise

Advancing Mathematics Research with AI-Driven Formal Proof Search

Generative Recursive Reasoning: Probabilistic Pathways Through Latent Space

cedar: Supercharging Machine Learning Data Pipelines

iGniter: Taming GPU Interference for Predictable Cloud Inference

HRM-Text: Efficient Pretraining Beyond Scaling

Probabilistic Tiny Recursive Model: Test-Time Compute Scaling for Iterative Reasoning

Stable Audio 3: Fast, Variable-Length Audio Generation

General Preference Reinforcement Learning

Breaking Erdős: A 1.014 Exponent for Unit Distances

RT-Splatting: Unified Reflection-Transmission Modeling with Gaussian Splatting

Goldstone Modes: How Physics Unlocks Deep Network Trainability

Learning Causal World Models with State Space Models

VGGT-Omega: Scaling Laws Meet 3D Reconstruction

Chrome Extension