This work proposes Code Comprehensor, a hybrid retrieval-reasoning framework combining CodeGraph, a code dependency callgraph, CodeScribe, which uses code-aware LLMs to generate hierarchical documentation across repository call graphs, and CodeContrast, a CLIP-style dual-encoder model trained on CodeScribe output to le...
Sujoy Roychowdhury, Joseph H. R. Isaac, Jian-Ning Gao et al.· 0 citations
This work takes the context and the teacher's answer as input, and generates the reasoning trace ourselves, in the style of the student's own model family, suspect that reasoning written in the student's family style is easier for it to learn from.
This work introduces WhatIf-Bench, a benchmark measuring how well forecasters use covariates to forecast a target's response to future events, and reveals generalization to Novel futures as the core challenge, and offers a testbed toward arbitrary scenario analysis.
Arjun Ashok, Mihir Parmar, Palash Goyal et al.· 0 citations
Medical vision-language models (VLMs) are evaluated on public benchmarks whose images and question-answer pairs have been freely available for years, yet reported accuracy assumes that these examples were not in the training data. We test this assumption for open VLMs on SLAKE-En, PathVQA, and VQA-RAD, and on a public...
Bruce Changlong Xu, Lan Wu, Alexander Ryu· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces Projection agents, a GCO methodology built on the Wolpertinger framework and adapted to a shared GNN-based latent space for observations and actions, and releases LaGCO-RL, a Python library that automates latent action-space construction and supports existing RL-GCO solutions, promoting reproducibi...
F. Terranova, Guillermo Bern'ardez, Albert Cabellos-Aparicio et al.· arXiv.org· 0 citations
The results suggest that training explicitly for saliency is a promising route towards chain-of-thought reasoning that is more faithful to the model's actual decision process.
M. Höth, Kristian Kersting, Bjorn Deiseroth et al.· arXiv.org· 1 citation
This paper defines this iterative inference process as Markovian generation chains, where each step takes a specific prompt template and the previous output as input, without including any prior data.
Mingmeng Geng, Amr Mohamed, Guo-Kan Shang et al.· arXiv.org· 3 citations
This work introduces SleepMaMi, a Sleep Foundation Model engineered to master both hour-long sleep architectures and fine-grained signal morphologies, demonstrating superior generalizability and label-efficient adaptation for clinical sleep analysis.
Keondo Park, Younghoon Na, You Rim Choi et al.· arXiv.org· 1 citation· ⚡1
This work proposes GFlowPO, a probabilistic prompt optimization framework that casts prompt search as a posterior inference problem over latent prompts regularized by a meta-prompted reference-LM prior and consistently outperforms recent discrete prompt optimization baselines.
Junmo Cho, Suhan Kim, Sangjune An et al.· arXiv.org· 0 citations
The commercialization of LLM applications is the next frontier in online advertising, with LLM-native advertising emerging as a promising paradigm by integrating ads into LLM-generated content. However, classic mechanisms are no longer applicable in this setting where the auction object is shifted from discrete ad slot...
Chujie Zhao, Qun Hu, Shiping Song et al.· 0 citations
The identification and localization of errors is a core task in peer review, yet the exponential growth of scientific output has made it increasingly difficult for human reviewers to reliably detect errors given the limited pool of experts. Recent advances in Large Language Models (LLMs) have sparked interest in their...
Sarina Xi, Vishisht Rao, Justin Payan et al.· 0 citations
How can we teach large multimodal models (LMMs) new skills without erasing prior abilities? We study sequential fine-tuning on five target skills while monitoring general ability on eight held-out benchmarks across three model families. Surprisingly, we find that performance lost on held-out tasks after fine-tuning on...
Zhen Zhu, Yiming Gong, Yao Xiao et al.· 0 citations
