14
Persona Matters: Effects of Activation Steering on Short Answer Generation and Scoring
A new study examines the impact of activation-based persona steering on short-answer generation and automated grading across three language models.
14
Bridging Cognitive Neuroscience and Graph Intelligence: Hippocampus-Inspired Multi-View Hypergraph Learning for Web Finance Fraud
Inspired by cognitive neuroscience, this paper proposes a multi-view hypergraph learning method to improve the detection of online financial fraud.
14
OREN: Octree Residual Network for Real-Time Euclidean Signed Distance Mapping
The Octree Residual Network enables real-time, differentiable Euclidean signed distance function reconstruction from point cloud data for robotic autonomy.
14
TNODEV: Toolbox for Neural ODE Verification
The TNODEV toolbox has been introduced to enable the formal verification and iterative reachability analysis of neural ordinary differential equations in safety-critical systems.
14
SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection
SimRPD is a new framework designed to optimize proactive recruitment dialogue agents by evaluating and selecting high-quality training data using a simulator.
14
EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models
Researchers have developed EasyLens, a training-free, plug-and-play tool designed to enhance the sensitivity of medical vision-language models to subtle clinical lesions.
14
ArtMine: Discovering and Formalizing Artistic Processes
ArtMine is a framework designed to analyze and formalize the iterative decision-making processes of creating art rather than just modeling the final visual output.
14
Data for Agents
Hugging Face has published an analysis focusing on the role and preparation of training data specifically optimized for artificial intelligence agents.
14
Building and connecting a production-ready ecommerce MCP server using Amazon Bedrock AgentCore and Mistral AI Studio
This technical guide explains how to build and deploy an e-commerce Model Context Protocol server using Amazon Bedrock AgentCore and Mistral AI Studio.
14
Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT
The study introduces adversarial decoys, a method designed to bypass attention-based defenses in Vision Transformers by misdirecting token suppression mechanisms.
14
XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision
The XFACTORS framework combines contrastive supervision with the information bottleneck principle to achieve stable and scalable disentangled representation learning.
14
Graph-Regularized Deep Learning for EEG-Based Emotion Recognition with Psychologically-Grounded Label Structure
A new graph-regularized learning framework incorporates psychological interdependencies among emotion classes to improve EEG-based emotion recognition.
14
Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution
A new framework aims to improve the explainability of temporal graph networks by analyzing how historical events stored in memory modules influence model predictions.
14
Psychological Competence as a Missing Dimension in AI Evaluation
This paper argues that current AI evaluation frameworks should expand beyond technical metrics to include psychological competence for models interacting directly with humans.
14
MambaLIE: Scene Light Intensity-Boosted Low-Light Image Enhancement with State Space Model
Researchers have introduced MambaLIE, a state space model-based framework designed to enhance low-light images by leveraging scene light intensity.
14
Generalization in offline RL: The structure is more important than the amount of pessimism
This paper demonstrates that optimal generalization in offline reinforcement learning depends on the structure of the pessimistic bias rather than the absolute level of conservatism.
14
Temporal Preference Concepts and their Functions in a Large Language Model
This work localizes the internal subgraph responsible for representing and resolving temporal preferences and trade-offs within a distilled large language model.
14
Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition
This paper introduces second-order actor-critic methods utilizing policy Hessian decomposition to accelerate convergence in discounted Markov decision processes.
14
Robust Weighted Triangulation of Causal Effects Under Model Uncertainty
The paper proposes a robust weighted triangulation method to improve causal effect estimation when dealing with model uncertainty in observational data.
14
Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning
Researchers have introduced a regularization method to improve offline agent alignment in imitation learning by leveraging human feedback and demonstrations.
14
Alignment Plausibility: A New Standard for Assuring AI in Healthcare
Researchers propose a new evaluation standard to address long-term risks and engagement-driven biases in healthcare-focused large language models.
14
How Causal Abstraction Underpins Computational Explanation
This paper argues that causal abstraction theory provides a valuable framework for explaining how neural networks implement specific computational processes.
14
Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning
A comprehensive survey evaluates the progress of large language models in medical reasoning by mapping clinical competencies to computational methods.
14
Context Graphs for Proactive Enterprise Agents
Researchers propose using a live relational data structure called a Context Graph to enable enterprise AI agents to proactively share information before being asked.