ICLR - arXivDaily 期刊&会议

2410.11779 2025-02-25 cs.CL cs.AI cs.CV cs.LG cs.MM

MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

Chenxi Wang, Xiang Chen, Ningyu Zhang, Bozhong Tian, Haoming Xu, Shumin Deng, Huajun Chen

Comments ICLR 2025

2410.10414 2025-02-25 cs.CR cs.CL cs.LG

On Calibration of LLM-based Guard Models for Reliable Content Moderation

Hongfu Liu, Hengguan Huang, Xiangming Gu, Hao Wang, Ye Wang

Comments Accepted to ICLR 2025

2410.07869 2025-02-25 cs.CL cs.AI cs.HC cs.LG cs.MA

Benchmarking Agentic Workflow Generation

Shuofei Qiao, Runnan Fang, Zhisong Qiu, Xiaobin Wang, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen

Comments ICLR 2025

2410.01524 2025-02-25 cs.CL cs.LG

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

Seanie Lee, Haebin Seong, Dong Bok Lee, Minki Kang, Xiaoyin Chen, Dominik Wagner, Yoshua Bengio, Juho Lee, Sung Ju Hwang

Comments ICLR 2025

2410.01316 2025-02-25 math.NA cs.LG cs.NA stat.CO stat.ML

Fast Summation of Radial Kernels via QMC Slicing

Johannes Hertrich, Tim Jahn, Michael Quellmalz

Comments Published as a conference paper at ICLR 2025

2409.19913 2025-02-25 cs.LG cs.AI cs.CL

Scaling Optimal LR Across Token Horizons

Johan Bjorck, Alon Benhaim, Vishrav Chaudhary, Furu Wei, Xia Song

Comments Accepted at ICLR 2025

2409.18582 2025-02-25 cs.LG cs.AI cs.NE q-bio.BM q-bio.QM

Optimistic Games for Combinatorial Bayesian Optimization with Application to Protein Design

Melis Ilayda Bal, Pier Giuseppe Sessa, Mojmir Mutny, Andreas Krause

Comments Accepted at the International Conference on Learning Representations (ICLR 2025)

2409.04185 2025-02-25 cs.LG cs.CL

Residual Stream Analysis with Multi-Layer SAEs

Tim Lawson, Lucy Farnik, Conor Houghton, Laurence Aitchison

Comments ICLR 2025 Camera Ready. 45 pages, 41 figures

2406.12120 2025-02-25 cs.LG cs.AI stat.ML

Adding Conditional Control to Diffusion Models with Reinforcement Learning

Yulai Zhao, Masatoshi Uehara, Gabriele Scalia, Sunyuan Kung, Tommaso Biancalani, Sergey Levine, Ehsan Hajiramezanali

Comments ICLR 2025

2406.04273 2025-02-25 cs.CV cs.AI

ELFS: Label-Free Coreset Selection with Proxy Training Dynamics

Haizhong Zheng, Elisa Tsai, Yifu Lu, Jiachen Sun, Brian R. Bartoldson, Bhavya Kailkhura, Atul Prakash

Comments Accepted to ICLR 2025

2406.04068 2025-02-25 cs.LG math.ST stat.ML stat.TH

Reassessing How to Compare and Improve the Calibration of Machine Learning Models

Muthu Chidambaram, Rong Ge

Comments ICLR 2025, 29 pages, 14 figures

2405.20777 2025-02-25 cs.CR cs.LG

Black-Box Detection of Language Model Watermarks

Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev

Comments ICLR 2025

2502.16223 2025-02-25 cs.CV

Prompt as Knowledge Bank: Boost Vision-language model via Structural Representation for zero-shot medical detection

Yuguang Yang, Tongfei Chen, Haoyu Huang, Linlin Yang, Chunyu Xie, Dawei Leng, Xianbin Cao, Baochang Zhang

Comments Accepted as ICLR 2025 conference paper

2502.16105 2025-02-25 cs.CV cs.AI

NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions

Tue M. Cao, Nhat X. Hoang, Hieu H. Pham, Phi Le Nguyen, My T. Thai

Comments The Thirteenth International Conference on Learning Representations

2502.16021 2025-02-25 cs.DS cs.LG

Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees

Gautam Chandrasekaran, Adam R. Klivans, Lin Lin Lee, Konstantinos Stavropoulos

Comments To appear in The Thirteenth International Conference on Learning Representations (ICLR 2025) 38 pages

2502.15760 2025-02-25 cs.LG

Digi-Q: Learning Q-Value Functions for Training Device-Control Agents

Hao Bai, Yifei Zhou, Li Erran Li, Sergey Levine, Aviral Kumar

Comments Accepted to ICLR 2025

2502.06501 2025-02-25 cs.CV

Learning Clustering-based Prototypes for Compositional Zero-shot Learning

Hongyu Qu, Jianan Wei, Xiangbo Shu, Wenguan Wang

Comments Accepted to ICLR 2025; Project page: https://github.com/quhongyu/ClusPro

2411.05172 2025-02-25 cs.CL

ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentence

Yuxin Wang, Xiaomeng Zhu, Weimin Lyu, Saeed Hassanpour, Soroush Vosoughi

Comments Accepted to ICLR 2025

2411.02571 2025-02-25 cs.CL cs.AI cs.CV cs.IR cs.LG

MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs

Sheng-Chieh Lin, Chankyu Lee, Mohammad Shoeybi, Jimmy Lin, Bryan Catanzaro, Wei Ping

Comments Accepted at ICLR 2025. We release the model weights at: https://huggingface.co/nvidia/MM-Embed

2411.02306 2025-02-25 cs.LG cs.AI

On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback

Marcus Williams, Micah Carroll, Adhyyan Narang, Constantin Weisser, Brendan Murphy, Anca Dragan

Comments Accepted to ICLR 2025

2410.13178 2025-02-25 cs.LG cs.AI

GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation

Ziwei Yang, Zheng Chen, Xin Liu, Rikuto Kotoge, Peng Chen, Yasuko Matsubara, Yasushi Sakurai, Jimeng Sun

Comments Published as a conference paper at ICLR 2025

2410.09508 2025-02-25 cs.CL cs.CY

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

Jiamu Zheng, Jinghuai Zhang, Tianyu Du, Xuhong Zhang, Jianwei Yin, Tao Lin

Comments 20 pages, 11 figures. Published as a conference paper at ICLR 2025. Code at https://github.com/LINs-lab/CollabEdit

2410.06270 2025-02-25 cs.LG cs.CL

Mixture Compressor for Mixture-of-Experts LLMs Gains More

Wei Huang, Yue Liao, Jianhui Liu, Ruifei He, Haoru Tan, Shiming Zhang, Hongsheng Li, Si Liu, Xiaojuan Qi

Comments ICLR 2025

2408.15240 2025-02-25 cs.LG

Generative Verifiers: Reward Modeling as Next-Token Prediction

Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, Rishabh Agarwal

Comments ICLR 2025

2408.03124 2025-02-25 eess.SY cs.LG cs.SY

CL-DiffPhyCon: Closed-loop Diffusion Control of Complex Physical Systems

Long Wei, Haodong Feng, Yuchen Yang, Ruiqi Feng, Peiyan Hu, Xiang Zheng, Tao Zhang, Dixia Fan, Tailin Wu

Comments Published as a conference paper at ICLR 2025

2407.02408 2025-02-25 cs.CL cs.LG

CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models

Song Wang, Peng Wang, Tong Zhou, Yushun Dong, Zhen Tan, Jundong Li

Comments ICLR 2025 Soptlight

2406.02540 2025-02-25 cs.CV

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

Tianchen Zhao, Tongcheng Fang, Haofeng Huang, Enshu Liu, Rui Wan, Widyadewi Soedarmadji, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning, Yu Wang

Comments Accepted at ICLR 2025, Project Page: https://a-suozhang.xyz/viditq.github.io/

2405.01848 2025-02-25 cs.IR cs.LG

RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank

Tanya Chowdhury, Yair Zick, James Allan

Comments ICLR 2025

2502.15618 2025-02-24 cs.CL cs.AI cs.LG

Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing

Qi Le, Enmao Diao, Ziyan Wang, Xinran Wang, Jie Ding, Li Yang, Ali Anwar

Comments ICLR 2025

2502.15370 2025-02-24 cs.CV

Weakly Supervised Video Scene Graph Generation via Natural Language Supervision

Kibum Kim, Kanghoon Yoon, Yeonjun In, Jaehyeong Jeon, Jinyoung Moon, Donghyun Kim, Chanyoung Park

Comments 10 pages, ICLR 2025