研究动态
Research radar论文、方法与技术进展，沿着关注的方向读下去。
快照采集于 北京时间 · 48 篇
阅读线索
共 48 篇 · 按发布日期
A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented Generation
Query clarification is essential for retrieval-augmented generation (RAG) systems that face ambiguous user queries. We consider multi-turn grounded conversational scenarios where a user query is either ill-formed or ambiguous in the…
Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds
Scaling data, diversity and model capacity has improved embodied learning in physical environments, where diverse experiences remain grounded in shared physical laws. Whether these gains extend to virtual worlds with different visual…
SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery
LLM-driven evolutionary search is a promising paradigm for scientific discovery, but existing methods remain costly and slow, often applying expensive reasoning uniformly while underusing evidence from failed, redundant, and saturated…
Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?
Frontier coding agents are increasingly framed as end-to-end automated researchers, and ML for science offers a demanding test of that promise: improving a scientific model often requires domain insight beyond routine ML engineering. We…
Forging More Tasks into Better Harnesses: Agentic Harness Evolution via Successive Scale Racing
Agentic harness evolution optimizes an agent's instructions, tools, and control flow by using its task execution experiences as evolving evidence. While more evolution tasks should intuitively improve performance, our preliminary study…
Decision language models as affordable and rapid alternatives to LLM judges of clinical generative AI
Automated judges of clinical artificial intelligence (AI) outputs are necessary, but large language model (LLM) judges are costly and slow at scale. We compared Jev, a decision language model that returns structured judgments, with…
Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysis
This study proposes a sketch-to-simulation system to solve handwritten circuit diagrams. The system converts raw images into a Simulation Program with Integrated Circuit Emphasis (SPICE)-compatible netlist and automatically calculates the…
Speedrunning Relational Foundation Model Pretraining
Progress on foundation model pretraining is gated by who can afford a trial, and relational pretraining is no exception. Recipes are developed inside individual labs, reported under private protocols, and do not accumulate. Speedrun…
To Manipulate or Not: Opinion Dynamics in LLM Interactions
Large language models increasingly take part in extended conversations where they can both shape and be shaped by another party's views, yet most persuasion research measures only one side of that exchange. We introduce a controlled…
Fig: Automated Multiagent Behavior Elicitor
Many social evaluations for multiagent systems study behaviors as they emerge from environments instead of systematically intervening in the environment to elicit such behaviors. We introduce Fig (Finding Interactions in Games), an…
Hidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication
Diffusion language models form answers through a sequence of revisable continuous states, but multi-agent systems usually discard those states and make agents communicate only after decoding text. We ask whether one independent diffusion…
DiffResearch: Accelerating Deep Research with Diffusion Language Models
Deep research systems iteratively plan, gather evidence, synthesize, and revise, making end-to-end latency a key bottleneck for interactive use. Almost all production systems are built on autoregressive (AR) language models and inherit…
Broad access through consistent standards
How OpenAI works with distribution partners to uphold consistent safeguards, support responsible access, and clarify expectations in our Usage Policies.
NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required
How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications
How AT&T is rethinking in-house legal work with OpenAI
AT&T is working with OpenAI to make legal knowledge easier to access. Learn how its LegalEdge team is rethinking intake and scaling legal judgment.
Profiling TorchNeuron (Part 1): System-level profiling on AWS Trainium.
Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster
ChatGPT Ads expands to 26 new countries as over 100,000 advertisers have used the platform
From local businesses to global brands, more advertisers can now reach people as they explore, compare and decide what to buy in ChatGPT.
OpenAI models are coming to Google Cloud
OpenAI and Google Cloud are bringing frontier models and Codex workflows to Gemini’s Model Garden, available through Google Cloud Marketplace.
Patch the Planet: global response coordination as agents uncover critical vulnerabilities
Patch the Planet connects security researchers, maintainers, and incident responders to help address critical vulnerabilities across open source.
How we built ChatGPT’s novel ad stack for user trust and relevance
Learn how OpenAI built ChatGPT’s LLM-powered ad stack to understand conversational intent, keep ads separate from answers, and deliver relevant ads at scale.
Using thousands of AI agents to uncover new leads in biological data
See how OpenAI, PerturbAI, and Scripps Research used distributed AI agents to uncover promising research leads in data from millions of brain cells.
Cloudflare links vulnerability discovery to defense with OpenAI
Cloudflare uses OpenAI Daybreak to investigate vulnerabilities and propose fixes for review. Its developers use Codex to build faster and improve code quality.
Democratic governance of frontier AI, part II: Empowering cyber defenders
OpenAI outlines a blueprint for empowering cyber defenders with frontier AI, stronger safeguards, modernized cybersecurity, and more resilient public institutions.
FairStress: A deeper evaluation of fairness in LLM decision-making
Franchisee reconciles cash in 94% less time with ChatGPT Work
An independent Schlotzsky’s and Cinnabon franchisee cut menu repricing time by 95% and built a workflow that could free up $100K in cash flow.
Terminal X matches senior investor judgment 88.6% with GPT-6.1
Terminal X’s Eval Agent grades outputs against a 54-criterion rubric, catching 25% more deviances from a fund’s mandate with GPT-6.1 Sol.
OpenAI acquires Orchestra Bio
OpenAI is acquiring Orchestra Bio to bring AI-powered operations to life sciences R&D, helping biopharma teams accelerate drug development and advance new treatments.
Hugging Face ❤️ TorchTPU: TPUs, Natively
AnyLanguageModel 1.0: One Year of Local Models on Apple Platforms
MPS in PyTorch 2.15
TorchNeuron: running HF models on AWS Trainium is easier than ever
Welcome Beam: a 501B open model you can own, customize, and scale
Accelerating the search for antimicrobial peptides with Google Antigravity
Accelerating the search for novel antimicrobial peptides using Google Antigravity for Science.
Apertus 1.5 Release Notes
Google DeepMind and Singapore Government collaborate to build fine-tuned AI model for scam detection
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
Developing Gemini 4 Argon responsibly and safely
Gemini 4 Argon for Robotics
Gemini 4 Argon: Built to solve your hardest problems
EmbeddingGemma 2: an open, lightweight multimodal embedding model
Gemini 4 Argon: our next era of frontier intelligence
Introducing SynthID Bio
Proof of concept for watermarking AI-generated proteins while preserving biological function.
Introducing Gemini 3.8 Live with Live Avatar
Advancing Private AI Compute with secure, server-side memory
Introducing private, server-side memory to Private AI Compute for personal AI.
Gemini 3.8 text-to-speech says hello
Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking