AI
presto: Efficient, Training-free, and Open-world Object Placement via Imaginary Search
Researchers have developed a new framework called presto for placing objects in images. Unlike previ...
AI
Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents
Researchers have developed a method to prevent large language models from recovering forgotten infor...
AI
Automating Multi-Hop RAG Evaluation via TRIAD: From Context Extraction to Validated Dataset Generation
Researchers have developed TRIAD, a method for automatically generating datasets for evaluating mult...
AI
Anchoring Bias: A Persistent Fairness Backdoor Attack against MLLMs under Continual Learning
Researchers have discovered a way to create a 'backdoor' in multimodal large language models (MLLMs)...
AI
Power-Performance Characterization of TinyML Systems
Researchers have analyzed the performance and power consumption of TinyML system...
AI
Why This, Not That? Mining User Profiles for Pair-wise Counterfactuals
Researchers propose a new task in recommender systems called pairwise interpreta...
AI
SynEHR: Joint Modeling Inter-visit Temporal Evolution and Intra-visit Clinical Structure for Longitudinal EHR Synthesis
Researchers have developed a new framework called SynEHR for synthesizing electr...
AI
Read, Write, Relax: Why Neural PDE Surrogates Need Both Global and Local Processing
Researchers have developed a new neural network model called Read-Write-Relax (R...