Category
3,200 papers
Blinded physician evaluation has been considered by many to be the gold standard for assessing clinical reasoning in large language models (LLMs). This is difficult to scale; thus, prior studies typically rely on small physician panels, often from a single institution or specialty, which both limits the scientific ques...
The Graph Theory Agent (GTA), which pairs a preference-trained representation selector with plan-and-decompose scaffolding around a frozen executor LLM, is proposed, which lifts Phi-4 from 53.5% to 69.1% on the benchmark's easy split and from 33.0% to 41.5% on its hard split.
This work asks whether a self-architecting transformer, which grows its own width and depth from quantitative signals derived from the attention matrices, can extract competitive protein representations from a single reference proteome.
CARE-MoE is proposed, an efficient MoE LLM inference framework comprising two core components that balances expert placement by jointly modeling co-activation correlation and hot–cold drift, preventing overload from correlated experts and enabling low-cost adaptive rebalancing.
Reach audiences
Advertise in front of researchers, engineers, and readers.
MIGServe treats the physical layout of MIG instances as a first-class scheduling dimension through three techniques: buddy-aware partition placement, which preserves large contiguous free blocks by allocating next to existing occupied buddies; proactive pair-matching migration, which consolidates fragmented half-full b...
A Multi-State Semantic Cache (MSSC) framework that dynamically maps knowledge chunks into three mutually exclusive states: zero cache, index cache, and full cache is proposed that reduces average service latency by over 40% in dynamic scenarios and suppresses backhaul reconfiguration traffic by up to 38% compared to co...
A sail is pushed by the wind, so a boat cannot outrun the wind──so it seems. This paper shows that changing only the heading removes the cap──neither the wind nor the sail is altered at all. No new theorem or law is claimed. Scope of this paper (scope note): No new theorem or law is claimed──apparent wind, propulsion b...
The Hall--Petch relation says finer grains are stronger, and it reverses at 10 to 30 nm. This paper shows that the reversal is not because the theoretical strength was reached──the prediction there does not even reach 14 per cent of it. No new theorem or law is claimed. Scope of this paper (scope note): No new theorem...
Analysis scripts accompanying the study “Dissociation Between Clinical Decision Accuracy and Citation Reliability Across Large Language Models in Small Renal Mass Management.” The scripts reproduce the statistical analyses reported in the manuscript, including inter-rater reliability (Cohen’s kappa), model comparisons...
We demonstrate that the weight matrices of multiple large language models sharing the same architecture but trained for different purposes (code generation vs conversational instruction-following) occupy a shared low-rank manifold. By computing a joint eigenspace (via SVD) across model weights, we factor N separate mod...
We demonstrate that the weight matrices of multiple large language models sharing the same architecture but trained for different purposes (code generation vs conversational instruction-following) occupy a shared low-rank manifold. By computing a joint eigenspace (via SVD) across model weights, we factor N separate mod...
Humidity rising sounds like water being added. This paper shows that the humidity can be taken to 100 per cent with the amount of water untouched──it is enough to lift the air. No new theorem or law is claimed. Scope of this paper (scope note): No new theorem or law is claimed──the lifting condensation level, the dry a...
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.
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.
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring 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.
