Generative AI

Report says Minnesota workers face highest generative AI exposure in the Midwest

A report from North Star Policy Action says Minnesota workers have the highest generative AI exposure in the Midwest and the 10th-highest...

Navigating Recent Developments in Generative AI and Trade Secret Protection

[2601.03127] Unified Thinker: A General Reasoning Modular Core for Image Generation

Abstract page for arXiv paper 2601.03127: Unified Thinker: A General Reasoning Modular Core for Image Generation

[2602.16699] Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents

The paper presents a framework called Calibrate-Then-Act (CTA) that enables LLMs to optimize decision-making by balancing cost and uncert...

[2602.16650] Retrieval Augmented Generation of Literature-derived Polymer Knowledge: The Example of a Biodegradable Polymer Expert System

This article presents a novel approach to extracting polymer knowledge from literature using Retrieval-Augmented Generation (RAG) techniq...

[2602.16634] Enhanced Diffusion Sampling: Efficient Rare Event Sampling and Free Energy Calculation with Diffusion Models

The paper presents Enhanced Diffusion Sampling, a novel method for efficient rare event sampling and free energy calculation in molecular...

[2602.16601] Error Propagation and Model Collapse in Diffusion Models: A Theoretical Study

This theoretical study examines error propagation and model collapse in diffusion models, highlighting how recursive training on syntheti...

[2602.16490] From Growing to Looping: A Unified View of Iterative Computation in LLMs

This paper explores the relationship between looping and depth growing in large language models (LLMs), proposing a unified view that hig...

[2602.16346] Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents

This article presents STING, a framework for evaluating illicit assistance in multi-turn, multilingual LLM agents, highlighting the chall...

[2602.16485] Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling

The paper introduces 'Team-of-Thoughts', a novel multi-agent system architecture that enhances performance by leveraging heterogeneous ag...

[2602.16467] IndicEval: A Bilingual Indian Educational Evaluation Framework for Large Language Models

IndicEval introduces a bilingual evaluation framework for large language models, assessing their performance on real examination question...

[2602.16422] Automated Histopathology Report Generation via Pyramidal Feature Extraction and the UNI Foundation Model

This article presents a novel framework for generating histopathology reports using a combination of a foundation model and a Transformer...

[2602.16132] CHAI: CacHe Attention Inference for text2video

The paper presents CHAI, a novel approach to enhance text-to-video generation by utilizing Cache Attention for efficient inference, achie...

[2602.16307] Generative AI Usage of University Students: Navigating Between Education and Business

This study explores the use of generative AI by university students balancing education and work, highlighting its benefits and challenges.

[2602.16113] Evolutionary Context Search for Automated Skill Acquisition

The paper presents Evolutionary Context Search (ECS), a novel method for automated skill acquisition in large language models, enhancing ...

[2602.16241] Are LLMs Ready to Replace Bangla Annotators?

This article evaluates the effectiveness of Large Language Models (LLMs) as annotators for Bangla hate speech, revealing significant bias...

[2602.16080] Surgical Activation Steering via Generative Causal Mediation

This article presents Generative Causal Mediation (GCM), a novel approach for steering language model behaviors by identifying and manipu...

[2602.16054] CLAA: Cross-Layer Attention Aggregation for Accelerating LLM Prefill

The paper introduces Cross-Layer Attention Aggregation (CLAA) to enhance the efficiency of long-context LLM inference by addressing token...

[2602.16038] Heuristic Search as Language-Guided Program Optimization

The paper presents a structured framework for Language-Guided Program Optimization, improving Automated Heuristic Design in combinatorial...

[2602.16140] Human-AI Collaboration in Large Language Model-Integrated Building Energy Management Systems: The Role of User Domain Knowledge and AI Literacy

This study explores how user domain knowledge and AI literacy influence the effectiveness of human-AI interactions in building energy man...

[2602.16136] Retrieval Collapses When AI Pollutes the Web

The paper discusses the phenomenon of 'Retrieval Collapse,' where AI-generated content dominates search results, leading to a decline in ...

[2602.15922] World Action Models are Zero-shot Policies

The paper introduces DreamZero, a World Action Model (WAM) that enhances zero-shot policy learning for robotic tasks by predicting future...

[2602.16033] Transforming GenAI Policy to Prompting Instruction: An RCT of Scalable Prompting Interventions in a CS1 Course

This article presents a randomized controlled trial (RCT) examining scalable prompting interventions in a CS1 course, highlighting the im...