research

A list of content tagged research

Responses

• Fara-7B: An Efficient Agentic Model for Computer Use
• SIMA 2: An Agent that Plays, Reasons, and Learns With You in Virtual 3D Worlds
• Exploring a space-based, scalable AI infrastructure system design
• MMCTAgent: Enabling multimodal reasoning over large video and image collections
• SentinelStep: Building agents that can wait, monitor, and act
• Diffusion Beats Autoregressive in Data-Constrained Settings
• VaultGemma: The world's most capable differentially private LLM
• Introducing Dreamer 4
• Introducing ChatGPT Pulse
• Qwen3-Omni
• Crescent library brings privacy to digital identity systems
• Self-Adapting Language Models (SEAL)
• Introducing deep research
• Microsoft Research: Introducing DRIFT Search
• Microsoft Research Focus: Week of October 28, 2024
• Thinking LLMs: General Instruction Following with Thought Generation
• Transformers in music recommendation
• TinyAgent: Function Calling at the Edge
• SAMMO: A general-purpose framework for prompt optimization
• ARAGOG: Advanced RAG Output Grading
• The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
• NightShade

Bookmarks

• DS-STAR: A state-of-the-art versatile data science agent
• Less is More: Recursive Reasoning with Tiny Networks
• ParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models
• Introducing Nested Learning: A new ML paradigm for continual learning
• Mathematical exploration and discovery at scale
• Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
• Graffiti: Enabling an Ecosystem of Personalized and Interoperable Social Applications
• Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing
• Tensor Logic: The Language of AI
• LoRA Without Regret
• Virtual Agent Economies
• How people use ChatGPT
• Introducing Locate 3D
• ZeroSearch - Incentivize the Search Capability of LLMs without Searching
• A Survey of AI Agent Protocols
• TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching
• CORG: Generating Answers from Complex, Interrelated Contexts
• Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks
• s1: Simple test-time scaling
• LongROPE: Extending LLM Context Window Beyond 2 Million Tokens
• Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
• DE-COP: Detecting Copyrighted Content in Language Models Training Data
• Using LLM to select the right SQL Query from candidates
• Large Language Models Are Zero-Shot Time Series Forecasters
• ReALM: Reference Resolution As Language Modeling
• GraphRAG: Unlocking LLM discovery on narrative private data
• LLM360: Towards Fully Transparent Open-Source LLMs
• Answer.AI - A new old kind of R&D lab
• PointLLM: Empowering Large Language Models to Understand Point Clouds
• Open challenges in LLM research