Category
8,685 papers
It is found that language distances provide a practical basis for equitable and performant transfer language selection, and are substantially reduced by training-free composite distances, and nearly eliminated by trained rankers.
Language models can now prove theorems, but people still decide which problems to pursue. We ask whether a model's internal representations can help identify promising mathematical connections. We develop LANTERN, a fast, cost-efficient pipeline that uses a classifier over pretrained-model activations to rank candidate...
Large language models (LLMs) can solve every intermediate step of a multi-step math problem on its own and still fail the full problem, even when given a roadmap of the steps and all of their answers. We introduce OracleLadder, a diagnostic evaluation that locates where LLM math reasoning fails by giving the model incr...
Triage decides who is seen first. Building an urgency classifier for patient-voice Kinyarwanda, we found our specification could be met without producing anything it was meant to secure. We report that, and the instruments that detect it, instead of a classifier. Designed for the four languages a Rwandan health centre...
Reach audiences
Advertise in front of researchers, engineers, and readers.
OptiArena is introduced, a budget-controlled testbed for studying whether LLMs can improve executable game-playing algorithms through five rounds of code edits within a fixed minimal scaffold and under bounded evaluator feedback and fixed resource budgets.
Who we communicate with influences both our interpretation of their utterances and the design of our own. Such adjustment to the conversational partner is studied as speaker modeling in comprehension and as audience design in production, with the two literatures having developed largely separately. We argue that both a...
This work finds that continuous regions of representation space not occupied by observed tokens become systematically structured from the earliest stages of learning, forming category-level geometric organization that supports generalization to unattested combinations.
This work proposes ScopeIF, a novel training framework for scope-aware precise instruction-following that enables optimized Qwen3-4B and 8B models to rival or surpass strong frontier models such as Gemini-2.5-Pro and DeepSeek-V3.2, establishing an effective paradigm for advancing scope-aware instruction-following.
This work systematically vary the context window size of GPT-2 across four large-scale naturalistic English reading-time datasets and observes a U-shaped relationship, demonstrating that tracking long-range coreference relations is one important factor for the alignment between LM surprisal and human reading behavior.
Voice agents depend on accurate automatic speech recognition (ASR) to act on what callers say, yet ASR is evaluated on read, English-centric speech with word error rate (WER), which penalizes surface rather than semantic differences. We introduce mu-bench, a dataset of 4,270 caller utterances from 250 phone calls to an...
PolAgentBench, a deterministic benchmark with Polish prompts and English tool schemas, is introduced and how GGUF quantization affects agentic tool use in Polish and whether the effects generalize across models is asked.
Contextual Early Reward (CER), which predicts terminal reward through behavioral evidence in a trajectory prefix, provides an interpretable, efficient, and dense evaluation method for long-horizon coding agents.
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.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
