Wispr Flow-Now on Android!
Mini toolsPapers
-
Slim attention: cut your context memory in half without loss – K-cache is all you need for MHA
-
Test-Time Training with KV Binding Is Secretly Linear Attention
-
Compositional Planning with Jumpy World Models
-
SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning
-
Toward the Thermodynamic Limit: Neural Operators for Non-equilibrium Dynamics of Mott Insulators
-
Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining
-
Haitao Lin
-
How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1
-
Wink: Recovering from Misbehaviors in Coding Agents
-
Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space
-
Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera ControlStanford University
-
The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning
-
SARAH: Spatially Aware Real-time Agentic Humans
-
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
-
El Agente Gráfico: Structured Execution Graphs for Scientific Agents
-
Unified Latents (UL): How to train your latents
-
EVMbench: Evaluating AI Agents on Smart Contract Security
-
EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
-
Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching
-
jina-embeddings-v5-text: Task-Targeted Embedding Distillation
-
World Action Models are Zero-shot Policies
-
On Surprising Effectiveness of Masking Updates in Adaptive Optimizers
-
GLM-5: from Vibe Coding to Agentic Engineering
-
Image Generation with a Sphere Encoder
-
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
-
Experiential Reinforcement Learning
-
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
-
Unifying Ranking and Generation in Query Auto-Completion via Retrieval-Augmented Generation and Multi-Objective Alignment
-
Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
-
WizardLM: Empowering large pre-trained language models to follow complex instructions
-
Florence: A New Foundation Model for Computer Vision
-
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
-
Visual Foresight for Robotic Stow: A Diffusion-Based World Model from Sparse Snapshots
-
On-Policy Context Distillation for Language Models
-
Iterative Reranking as a Compute-Scaling Method for LLM-based Rankers
-
KG-CRAFT: Knowledge graph-based contrastive reasoning with LLMs for enhancing automated fact-checking
-
Pattern Discovery with Wide-Lens Analysis and Sharp-Focus Validation
-
ChatLLM network: More brains, more intelligenceBeijing Institute of Technology
-
BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation
-
Voxtral Realtime
-
Accelerating Mathematical and Scientific Discovery with Gemini Deep Think
-
OmniSapiens: A Foundation Model for Social Behavior Processing via HARPOMIT, National University of Singapore
-
GameDevBench Evaluating Agentic Capabilities Through Game Development Wayne Chi1 , Yixiong Fang1 , Arnav Yayavaram1 , Siddharth Yayavaram1 , Seth Karten2Carniege Mellon University, Princeton University
-
EchoJEPA: A Latent Predictive Foundation Model for Echocardiography
-
Autoregressive Image Generation with Masked Bit Modeling
-
iGRPO: Self-Feedback–Driven LLM Reasonin
-
ML-DCN: Masked Low-Rank Deep Crossing Network Towards Scalable Ads Click-through Rate Prediction at Pinterest
-
Agentic LLMs as Powerful Deanonymizers: Re-identification of Participants in the Anthropic Interviewer Dataset
-
HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing
-
Intelligence Explosion
