Category
20,515 papers
This paper proposes a sparse relaxation method for RL (called SpaRLax), which leverages the differentiability of soft-CoT reasoning over time steps and makes training more stable and effective, and adopts an entmax sparsity method that adaptively determines the degree of softness.
Layer-Specific Adaptation with Prototype-Anchored Adapter-Space Transport (LSA-PAST) is proposed, a parameter-efficient method tailored to composition-IL that achieves state-of-the-art accuracy-forgetting trade-off performance for composition-IL.
A control variate built from a learned classifier of the outage, trained on cheap observable features such as temperature and load forecasts is proposed and shows that learned control variates can help planners design distribution grids that stay reliable against rare outages.
Transformer-based k-space motion-trajectory estimation enables fast retrospective correction of standard clinical TSE brain MRI and reduces visible artefacts while preserving anatomical detail.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Entropy-Driven Multimodal Answering (EDMA) is proposed, which uses logical entropy to formalise multimodal QA as an iterative process of entropy reduction and to quantify the contribution of each modality in distinguishing correct from incorrect candidate answers.
Paired Outcome-guided Reasoning Allocation (PORA), which learns this decision by comparing short and long reasoning from the same interaction state by comparing their final quality and total processing to estimate when longer reasoning is valuable.
PROVISO is presented, a controller that decides which action to commit after the agent proposes an action and before it is executed, and commits the action with the highest calibrated value learned from outcomes.
OWP is proposed, a training-free framework that shifts hallucination mitigation from output-level manipulation to conflict-conditioned representation rebalancing and adaptively rebalances fused representations by suppressing misleading priors and restoring ignored evidence before decoding.
Clinical System One (CS1), a 4-billion-parameter decision model for fast, typed judgments from clinical records, is presented, along with two agentic harnesses in which CS1 works together with a generalist language model.
ReuF2F is introduced, a Lean 4 benchmark of 244 formalized open problems drawn from Research Experiences for Undergraduates (REU), spanning entry-level open research problems across a broad range of mathematical subfields and adopts a standard coding-agent evaluation setting.
This monograph seeks to define physical AI, present its technical landscape, and examine each key technical subfield in depth, and establishes a unified framework for Physical AI: artificial systems that perceive, model, and act upon the physical world through continuous feedback under real-world constraints.
M-Plan is proposed, a closed-loop MAS framework that integrates long-term and short-term memory that enhances agents' performance on multi-turn tasks while maintaining a plug-and-play design and outperforms multiple baseline methods in both accuracy and efficiency.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
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.
