Category
9,568 papers
A token-level probability reweighting framework that, given access to logits and a small amount of task-specific data, can effectively steer black-box LLMs toward application-specific content generation and advocates for broader access to token logits in closed-source models.
We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as its core interaction: while reading a model response, the annotator locates the first inappropriate token and either picks a substitute from the model's candidate tokens...
Evaluation of Computer-Use Agents (CUAs) is often limited to the final deliverables they create (at the end of hundreds of steps) and assessed with functional verifiers, as seen in OSWorld. However, such evaluation of end-state performance lacks transparency into how and why agents fail in various tasks, obfuscating cr...
The results show that targeted synthetic datasets and rubric-based training can systematically improve both diagnostic and interactive clinical reasoning in medical LLMs.
Reach audiences
Advertise in front of researchers, engineers, and readers.
TAC-Time is proposed, a unified framework that transforms textual information into additional temporal channels that preserves temporal continuity and periodic structures while remaining efficient and scalable and identifies predictive textual signals whose correlation-aware alignment yields partial forecasting improve...
This work proposes a new paradigm called the Data Agent, designed to manage, process, and analyze data with minimal human intervention, and develops two specialized agents: the data analytics agent and the data science agent.
STEVE, a stabilization framework with two coupled mechanisms that reduces degradation and produces more robust prompts, provides a practical way to improve the stability and effectiveness of textual-gradient prompt optimization.
The paper shows that credible evaluation of financial language models requires an end-to-end engineering approach combining language understanding, temporal discipline, market-friction-aware deployment, and reproducible validation.
TrustMOPD replaces example-level teacher selection with label-free, token-level supervision allocation and closes the overall-score gap between the initial student and oracle-routed teachers when trained on single- and multi-teacher on-policy distillation.
Maintenance work orders must often be processed offline on embedded hardware, yet downstream software requires predictable structured output. We present ARID (Aviation-inspired Routing for Industrial Deployment), which extracts component, failure mode, symptom, and maintenance action into fixed-schema JSON on an 8 GB N...
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...
Natural Language Processing
Our most capable vision-language-action model enhances robot dexterity, reliability, and safety
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
