Category
8,685 papers
This work proposes NOSA, a trainable sparse attention mechanism natively designed for KV cache offloading that explicitly constrains the volume of CPU-GPU KV transfers, thereby achieving low communication overhead and high decoding throughput.
A controlled multilingual evaluation across six geographically, culturally, and linguistically diverse languages reveals a central disconnect in multilingual moral reasoning: language changes models'moral judgments and the training evidence associated with their reasoning, but does not correspondingly localize the mora...
This work introduces a novel PLM for political discourse language called RooseBERT, trained on large political debate and speech corpora in English, and fine-tuned it on multiple downstream tasks related to political debate analysis, highlighting how domain-specific pre-training enhances performance in political debate...
A computational-theoretical framework is established to provide an account of psychopathology applicable to LLMs and experiments suggest that network-theoretic computations of psychopathology may have emerged in LLMs.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces the cliff token, a token at which the estimated probability of reaching the correct answer (success probability) drops beyond an adaptive threshold, and introduces a cliff taxonomy of deterministic, uncertain, and sampled-off cliffs, defined by greedy choice and token entropy.
An evaluation framework AgentCL for continual learning in agents is presented, centered on distinguishable task streams and metrics for CL properties, and MemProbe is developed, a probing method that stores interactions, insights, and skills while filtering unreliable experiences during consolidation.
LLM-powered coding agents spend the majority of their token budget reading repository files, yet much of the retrieved code is irrelevant to the task at hand. Existing learned pruners compress this context with a single-objective sequence labeler, collapsing all facets of code relevance into one score and one transitio...
ScaleLogic is introduced, a synthetic logical reasoning framework that offers independent control over two axes of difficulty: the depth of the required proof planning and the expressiveness of the underlying formal system.
It is hypothesized that in long traces, hindsight reveals which steps were unnecessary more readily than which steps would have repaired the solution, and that changing the divergence, enriching or reinjecting the privileged context, and training longer only move OPSD along the same accuracy-length tradeoff.
BALAR (Bayesian Agentic Loop for Active Reasoning), a task-agnostic outer-loop algorithm that requires no fine-tuning and enables multi-turn interaction between an LLM agent and a user, is proposed.
It is found that task type is a stronger predictor of acceptance than tree depth, and chat produces the highest entropy yet the highest acceptance rate, which has direct implications for domain-aware speculation budgets and draft-model selection strategies.
MMORF is presented, a framework for constructing language model-based multi-agent systems (MAS) for multi-objective retrosynthesis planning that achieves strong safety and cost metrics on soft-constraint tasks, frequently Pareto-dominating baseline routes, and outperforming state-of-the-art baselines.
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.
