Category
17,191 papers
TTME is introduced, a plug-and-play test-time adaptation method that continually updates the external memory by distilling the experience to guide subsequent discovery without updating model weights, and established as an effective and computationally efficient alternative to TTT in the evaluated discovery settings.
Self-Direction is introduced, a mechanism for agents to learn from mistakes that combines the benefits of temporary in-context retries and policy updates and reduces repeated mistakes across future encounters of a task, nearly doubling the reliability of an agent's corrections.
Multimodal healthcare data contain relational information that extends beyond individual patient observations. Effective clinical outcome prediction therefore requires not only integrating information from multiple modalities, but also modeling the relationships between them. Standard fusion approaches do not explicitl...
Streaming data analytics helps businesses identify opportunities and spot risks in a timely fashion. As large language model (LLM) usage grows, people are exploring incorporating agents or LLMs in streaming data pipelines to help find patterns in datasets without supervision or interpret natural languages for content m...
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work presents ChemBART, a BART-based language model that adopts a reaction-centric pre-training strategy that unifies diverse chemical tasks to facilitate synthesis planning with comprehensive implementation information and highlights the potential of reaction-focused pre-training.
This work introduces an approach to apply Constitutional AI training with domain-specific mental health principles for safe, domain-adapted CAI systems in computational mental health applications.
This work proposes Code Comprehensor, a hybrid retrieval-reasoning framework combining CodeGraph, a code dependency callgraph, CodeScribe, which uses code-aware LLMs to generate hierarchical documentation across repository call graphs, and CodeContrast, a CLIP-style dual-encoder model trained on CodeScribe output to le...
KANs with Tractable Operators for Uncertainty and Constraints (TOUCKANs) are introduced, making statistical operators and integral constraints directly available within an expressive neural surrogate.
RangeNav is presented, a compact (183k parameters) LiDAR range-image encoder pretrained entirely on synthetic data that demonstrates robust navigation through dense crowds, low-light settings, and construction zones where limited-field-of-view depth policies struggle.
This work takes the context and the teacher's answer as input, and generates the reasoning trace ourselves, in the style of the student's own model family, suspect that reasoning written in the student's family style is easier for it to learn from.
Zero-shot cross-lingual voice cloning often carries the reference speaker's accent into the target language. We propose closed-loop dual-reference guidance, which pairs the original reference with a reusable native anchor constructed by voice conversion (VC). The references initialize separate language-model (LM) state...
This work asks how consulting memory during dialogue changes what users go on to say, and thus what the memory comes to reveal, and across four support models, memory raises response quality but also empirical leakage, the share of attribute values correctly inferred from the record, by a margin that widens over sessio...
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
A Blog post by Ai2 on Hugging Face
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
