Category
9,261 papers
Pseudo Self-Distillation is presented, a framework that enables small language models to construct hierarchical memory representations by distilling behavior from a strong black-box oracle through a multi-stage training pipeline, with off-policy PSD achieving the strongest results across most conditions.
A category-aware expert-training and policy-integration framework for repository-level software engineering that evaluates Pooled RL and Balanced RL, expert development, and single-model integration through aggregate and per-category resolution, the minimum category lift over each joint-RL baseline, and expert-gain rec...
This work introduces Machine-Interpretable Information (MII), the first agent-to-agent (A2A) document-to-state protocol, and demonstrates strong cross-model interoperability across heterogeneous LLMs -- despite the Writer using a legacy GPT-2 vocabulary, forcing genuine semantic translation rather than token-level memo...
Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through input--output behavior or input attributions, leaving internal computation largely underexplored. We instead cast faithfulness as internal concept grounding: Does a large lan...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller models handle equally well. Existing routing solutions optimize single-turn query assignment but ignore a property unique to agentic workflows: subtask complexity varies widely...
This work asks whether a learned per-query gate can skip the reranker where it will not help, using only features available before the LLM call with an executable fallback with an executable fallback.
These results identify the answer-token boundary, rather than semantic representation alone, as a measurable source of error in this benchmark, and introduce heterogeneous readout decomposition (HRD), which separates semantic verification from output realization.
A comparative study of machine learning and transformer-based approaches for clinical domain classification from medical transcriptions and provides a systematic comparison of classical machine learning, transformer models, and few-shot prompting for medical transcription analysis.
Knowledge distillation (KD) aims to compress high-performance teacher LLMs into lightweight students. However, distilled students often exhibit substantial performance degradation in out-of-distribution (OOD) settings, a critical gap that remains underexplored. We identify two compounding mechanisms causing OOD perform...
Behavioural evaluations of hosted language models can vary because the evaluated service, the measurement instrument, or both differ across runs. We separate three validation questions: whether a prior finding recurs on fresh data under its historical configuration (replication), whether the endpoint changes when the e...
A large audio language model (LALM) attaches a speech front end to a text language model (LM) that is already safety-aligned. When such a model refuses a harmful spoken request, is the refusal carried by the front end, or inherited from the text LM? We test this with causal interventions. At each model's audio-to-LM in...
Instruction hierarchy (IH) alignment teaches language models to prioritize higher-level instructions when inputs conflict. While studied primarily in text-only settings, vision-language models (VLMs) introduce new challenges for IH: instructions may be embedded in images, split across modalities, visually transformed,...
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
