大模型推理能力

DiffSpec: Differential Testing with LLMs using Natural Language Specifications and Code Artifacts

Nikitha Rao, Elizabeth Gilbert, Harrison Green, Tahina Ramananandro, Nikhil Swamy, Claire Le Goues, Sarah Fakhoury

专题命中 测试时计算 ：verifier(abstract)

Text-to-Image Alignment in Denoising-Based Models through Step Selection

Paul Grimal, Hervé Le Borgne, Olivier Ferret

机构 * Université Paris-Saclay, CEA, List（巴黎-萨克雷大学、法国原子能委员会、List） 纠错

专题命中 测试时计算 ：reasoning(abstract)

LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding

Ziyi Wang, Haoran Wu, Yiming Rong, Deyang Jiang, Yixin Zhang, Yunlong Zhao, Shuang Xu, Bo XU

专题命中 测试时计算 ：reasoning(abstract)

Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?

Tianyuan Qu, Longxiang Tang, Bohao Peng, Senqiao Yang, Bei Yu, Jiaya Jia

专题命中 测试时计算 ：reasoning(abstract)

Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection

Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Arsh Koneru, Yusuke Kato, Kazuki Kozuka, Aditya Grover

专题命中 测试时计算 ：reasoning(abstract)

Comments 17 pages, 9 figures

CoS: Chain-of-Shot Prompting for Long Video Understanding

Jian Hu, Zixu Cheng, Chenyang Si, Wei Li, Shaogang Gong

专题命中 测试时计算 ：reasoning(abstract)

Comments A training-free test-time optimisation approach for long video understanding

SampleLLM: Optimizing Tabular Data Synthesis in Recommendations

Jingtong Gao, Zhaocheng Du, Xiaopeng Li, Yichao Wang, Xiangyang Li, Huifeng Guo, Ruiming Tang, Xiangyu Zhao

专题命中 测试时计算 ：chain-of-thought(abstract)

VRank: Enhancing Verilog Code Generation from Large Language Models via Self-Consistency

Zhuorui Zhao, Ruidi Qiu, Ing-Chao Lin, Grace Li Zhang, Bing Li, Ulf Schlichtmann

专题命中 测试时计算 ：chain-of-thought(abstract)

Comments accepted by ISQED2025

ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models

Mingrui Wu, Xinyue Cai, Jiayi Ji, Jiale Li, Oucheng Huang, Gen Luo, Hao Fei, Guannan Jiang, Xiaoshuai Sun, Rongrong Ji

专题命中 测试时计算 ：reasoning(abstract)

Comments Accepted to NeurIPS 2024; Code:https://github.com/mrwu-mac/ControlMLLM

Sparse identification of evolution equations via Bayesian model selection

Tim W. Kroll, Oliver Kamps

专题命中 测试时计算 ：reasoning(abstract)

Comments 22 pages, 6 fgures

Hallucination Mitigation Prompts Long-term Video Understanding

Yiwei Sun, Zhihang Liu, Chuanbin Liu, Bowei Pu, Zhihan Zhang, Hongtao Xie

专题命中 测试时计算 ：chain-of-thought(abstract)

Streaming Long Video Understanding with Large Language Models

Rui Qian, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Shuangrui Ding, Dahua Lin, Jiaqi Wang

专题命中 测试时计算 ：reasoning(abstract)

Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision

Bobby Azad, Reza Azad, Sania Eskandari, Afshin Bozorgpour, Amirhossein Kazerouni, Islem Rekik, Dorit Merhof

专题命中 测试时计算 ：reasoning(abstract)

Comments The paper is currently in the process of being prepared for submission to MIA

Interaction-Aware Sampling-Based MPC with Learned Local Goal Predictions

Walter Jansma, Elia Trevisan, Álvaro Serra-Gómez, Javier Alonso-Mora

专题命中 测试时计算 ：planning(abstract)

Comments Accepted for presentation at the 2023 IEEE International Symposium on Multi-Robot & Multi-Agent Systems

What do LLMs need to Synthesize Correct Router Configurations?

Rajdeep Mondal, Alan Tang, Ryan Beckett, Todd Millstein, George Varghese

专题命中 测试时计算 ：verifier(abstract)

Do Not Return Similarity: Face Recovery with Distance

Mingtian Tan, Zhe Zhou

专题命中 测试时计算 ：verifier(abstract)

A Sampling-Based Approach to Computing Equilibria in Succinct Extensive-Form Games

Miroslav Dudik, Geoffrey Gordon

专题命中 测试时计算 ：reasoning(abstract)

Comments Appears in Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (UAI2009)