Found 46 document(s)
Page 2 of 4
-
Understanding human needs and selecting responses require distinct judgments that aggregate accuracy can obscure. We introduce PsycheMME, a video benchmark informed by psychology, with eight capabilities spanning groundi...
-
Multilingual large language models are increasingly deployed in settings where visible reasoning traces support verification, education, and safety auditing, yet standard evaluations typically measure only final-answer a...
-
Large language models (LLMs) have shown great potential as general-purpose user simulators for interactive systems. Prior studies have demonstrated that training on high-quality data can substantially improve model reaso...
-
A model's failures can reveal gaps in the behavioral criteria guiding its training. We introduce RubricOpt, a framework that lets a policy revise these criteria within preference optimization. The policy diagnoses its ow...
-
Recursive self-improvement (RSI) describes a system that improves not only its behavior but also the process by which it improves. Recent digital agents test this idea by rewriting their own code and checking each versio...
-
Currently, CT-guided lung biopsy is a highly manual procedure requiring patient breath-holding, iterative manual needle insertions, and repeated CT confirmation scans to accurately target a tumor. Automating this process...
-
What visual representation should a navigation policy act on? Navigation policies built on vision foundation models largely leave representation design to the encoders' pretraining objectives. We present RepresentNav, a ...
-
Vision language models (VLMs) have been increasingly adopted in consumer smart-home camera systems to interpret recorded videos and provide insights. However, video clips captured from smart-home cameras are different fr...
-
Multi-step predictions of future transition realizations can improve reinforcement learning, but their value remains difficult to quantify. Directly including these predictions in the state can lead to exponential state-...
-
Large language model (LLM)-based multi-agent systems have demonstrated remarkable capabilities across diverse tasks. Yet their memory and collaboration architectures often remain static, constraining continued adaptation...
-
Vision-language-action (VLA) models enable robots to follow instructions in typed text, limiting broader deployment in natural speech. The traditional solution by prepending a speech recognition before VLA to convert spe...
-
AI coding agents routinely clone repositories, install packages, and read source code obtained from the Web, so publicly hosted code becomes part of the context that shapes the code they write. We show that this Web-born...
-
Foundation models provide powerful representations for unstructured data, such as text and images, and parameter-efficient fine-tuning (PEFT) makes their adaptation to downstream tasks increasingly practical. For neural ...
-
ClinVerse: A Realistic Multi-Agent Diagnostic Environment for Training and Evaluating Medical AgentsDisease diagnosis is a key application of large language model (LLM) agents in healthcare. However, existing medical agents are primarily trained and evaluated with static question-answering data, providing limited oppor...