AI
AgentOCR: Reimagining Agent History via Optical Self-Compression
Researchers have developed AgentOCR, a framework that uses visual tokens to represent the history of an agent's interactions. This approach compresses...
AI
AI
GroupSegment-SHAP: Shapley Value Explanations with Group-Segment Players for Multivariate Time Series
Researchers have proposed a new method for explaining the predictions of multivariate time-series models called GroupSegment SHAP. This approach combi...
AI
CFM: Language-aligned Concept Foundation Model for Vision
Researchers have developed a new AI model called CFM that can understand the concepts behind images and provide explanations for its decisions. Unlike...
AI
Investigating Target Class Influence on Neural Network Compressibility for Energy-Autonomous Avian Monitoring
Researchers have proposed a method for monitoring bird species using machine learning models running on inexpensive microcontrollers in the field. The...
AI
Mind the Style: Impact of Communication Style on Human-Chatbot Interaction
Researchers conducted a study on how the tone of chatbots affects user experience and task success. They created two versions of a chatbot called NAVI...
AI
PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval
Researchers have created a new benchmark called PhotoBench to improve personalized photo retrieval. Unlike existing benchmarks that rely on web snapsh...
AI
Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration
Researchers have proposed a method called DiSE for self-evaluation of diffusion language models. DiSE works by calculating the probability that a gene...
AI
Efficient Exploration at Scale
Researchers have developed an online learning algorithm that significantly improves the data efficiency of reinforcement learning from human feedback....
AI
InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting
Researchers propose InverFill, a one-step inversion method for image inpainting that injects semantic information from the input masked image into the...
AI
DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis
Researchers have created a large-scale dataset called DF3DV-1K to help improve the development of 'distractor-free' vision systems. This dataset inclu...
AI
ChemGraph-XANES: An Agentic Framework for XANES Simulation and Curation
Researchers have developed ChemGraph-XANES, a framework for simulating and curating X-ray absorption near-edge structure (XANES) data. The agentic fra...
AI
Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Long-Horizon Workflows
Researchers have proposed using complete cyclic subtask graphs to improve the performance of large language model (LLM) agents in long-horizon tool-us...