ICLR Papers

6,124 papers found • Page 26 of 123

Fine-tuning can cripple your foundation model; preserving features may be the solution

Philip Torr, Puneet Dokania, Jishnu Mukhoti et al.

ICLR 2025posterarXiv:2308.13320
70
citations

Fine-tuning can Help Detect Pretraining Data from Large Language Models

Hengxiang Zhang, Songxin Zhang, Bingyi Jing et al.

ICLR 2025posterarXiv:2410.10880
4
citations

Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design

Chenyu Wang, Masatoshi Uehara, Yichun He et al.

ICLR 2025posterarXiv:2410.13643
42
citations

Fine-Tuning Token-Based Large Multimodal Models: What Works, What Doesn’t and What's Next

Zhulin Hu, Yan Ma, Jiadi Su et al.

ICLR 2025poster

Fine-tuning with Reserved Majority for Noise Reduction

Shuyang Jiang, Yusheng Liao, Ya Zhang et al.

ICLR 2025poster
2
citations

FIRING-Net: A filtered feature recycling network for speech enhancement

Xinmeng Xu, Yiqun Zhang, Jizhen Li et al.

ICLR 2025poster

First-Person Fairness in Chatbots

Tyna Eloundou, Alex Beutel, David Robinson et al.

ICLR 2025posterarXiv:2410.19803
20
citations

Fitting Networks with a Cancellation Trick

Jiashun Jin, Jingming Wang

ICLR 2025posterarXiv:2502.16728
1
citations

Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond

Costin-Andrei Oncescu, Sanket Jayant Purandare, Stratos Idreos et al.

ICLR 2025posterarXiv:2410.12982
2
citations

FlashMask: Efficient and Rich Mask Extension of FlashAttention

Guoxia Wang, Jinle Zeng, Xiyuan Xiao et al.

ICLR 2025posterarXiv:2410.01359

FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware

Korbinian Pöppel, Maximilian Beck, Sepp Hochreiter

ICLR 2025posterarXiv:2412.07752

Flat Reward in Policy Parameter Space Implies Robust Reinforcement Learning

HyunKyu Lee, Sung Whan Yoon

ICLR 2025poster

Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks

Nikolaos Tsilivis, Gal Vardi, Julia Kempe

ICLR 2025posterarXiv:2410.22069
5
citations

Flaws of ImageNet, Computer Vision's Favourite Dataset

Nikita Kisel, Illia Volkov, Kateřina Hanzelková et al.

ICLR 2025posterarXiv:2412.00076

FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models

Zhanwei Zhang, Shizhao Sun, Wenxiao Wang et al.

ICLR 2025posterarXiv:2411.05823

FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Xunhao Lai, Jianqiao Lu, Yao Luo et al.

ICLR 2025posterarXiv:2502.20766
51
citations

FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement Learning

Woosung Koh, Wonbeen Oh, Siyeol Kim et al.

ICLR 2025poster

FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model

Chongkai Gao, Haozhuo Zhang, Zhixuan Xu et al.

ICLR 2025posterarXiv:2412.08261
24
citations

FLOPS: Forward Learning with OPtimal Sampling

Tao Ren, Zishi Zhang, Jinyang Jiang et al.

ICLR 2025posterarXiv:2410.05966
2
citations

Flow-based Variational Mutual Information: Fast and Flexible Approximations

Caleb Dahlke, Jason Pacheco

ICLR 2025poster
4
citations

FlowDec: A flow-based full-band general audio codec with high perceptual quality

Simon Welker, Matthew Le, Ricky T. Q. Chen et al.

ICLR 2025posterarXiv:2503.01485
14
citations

Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors

Lin-Zhuo Chen, Kangjie Liu, Youtian Lin et al.

ICLR 2025posterarXiv:2502.07615
4
citations

Flow matching achieves almost minimax optimal convergence

Kenji Fukumizu, Taiji Suzuki, Noboru Isobe et al.

ICLR 2025posterarXiv:2405.20879
12
citations

Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting

Marcel Kollovieh, Marten Lienen, David Lüdke et al.

ICLR 2025oralarXiv:2410.03024
20
citations

Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective

Neta Shaul, Itai Gat, Marton Havasi et al.

ICLR 2025posterarXiv:2412.03487
35
citations

Flow: Modularized Agentic Workflow Automation

Boye Niu, Yiliao Song, Kai Lian et al.

ICLR 2025posterarXiv:2501.07834
21
citations

Flow With What You Know

Scott Hawley

ICLR 2025poster

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

Lijie Fan, Tianhong Li, Siyang Qin et al.

ICLR 2025posterarXiv:2410.13863
117
citations

Following the Human Thread in Social Navigation

Luca Scofano, Alessio Sampieri, Tommaso Campari et al.

ICLR 2025posterarXiv:2404.11327

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

Zhenting Qi, Hanlin Zhang, Eric P Xing et al.

ICLR 2025posterarXiv:2402.17840
47
citations

For Better or For Worse? Learning Minimum Variance Features With Label Augmentation

Muthu Chidambaram, Rong Ge

ICLR 2025posterarXiv:2402.06855

ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities

Ezra Karger, Houtan Bastani, Chen Yueh-Han et al.

ICLR 2025posterarXiv:2409.19839
34
citations

Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced Exploration

Qintong Li, Jiahui Gao, Sheng Wang et al.

ICLR 2025poster

Forget the Data and Fine-Tuning! Just Fold the Network to Compress

Dong Wang, Haris Šikić, Lothar Thiele et al.

ICLR 2025posterarXiv:2502.10216

Forgetting Transformer: Softmax Attention with a Forget Gate

Zhixuan Lin, Evgenii Nikishin, Xu He et al.

ICLR 2025posterarXiv:2503.02130

Forking Paths in Neural Text Generation

Eric Bigelow, Ari Holtzman, Hidenori Tanaka et al.

ICLR 2025posterarXiv:2412.07961
18
citations

FormalAlign: Automated Alignment Evaluation for Autoformalization

Jianqiao Lu, Yingjia Wan, Yinya Huang et al.

ICLR 2025posterarXiv:2410.10135
10
citations

Formation of Representations in Neural Networks

Liu Ziyin, Isaac Chuang, Tomer Galanti et al.

ICLR 2025posterarXiv:2410.03006
12
citations

Forte : Finding Outliers with Representation Typicality Estimation

Debargha Ganguly, Warren Morningstar, Andrew Yu et al.

ICLR 2025posterarXiv:2410.01322
4
citations

FOSP: Fine-tuning Offline Safe Policy through World Models

Chenyang Cao, Yucheng Xin, Silang Wu et al.

ICLR 2025posterarXiv:2407.04942
3
citations

Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models

Jeffrey Gu, Serena Yeung

ICLR 2025posterarXiv:2503.00838
3
citations

Fourier Head: Helping Large Language Models Learn Complex Probability Distributions

Nate Gillman, Daksh Aggarwal, Michael Freeman et al.

ICLR 2025posterarXiv:2410.22269

Fourier Sliced-Wasserstein Embedding for Multisets and Measures

Tal Amir, Nadav Dym

ICLR 2025posterarXiv:2405.16519
9
citations

Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models

Cong Fu, Xiner Li, Blake Olson et al.

ICLR 2025posterarXiv:2408.09730
10
citations

Framer: Interactive Frame Interpolation

Wen Wang, Qiuyu Wang, Kecheng Zheng et al.

ICLR 2025posterarXiv:2410.18978
20
citations

Frame-Voyager: Learning to Query Frames for Video Large Language Models

Sicheng Yu, CHENGKAI JIN, Huanyu Wang et al.

ICLR 2025posterarXiv:2410.03226
42
citations

FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling

zhengqiang ZHANG, Ruihuang Li, Lei Zhang

ICLR 2025posterarXiv:2410.18410

Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image Generation

Lokesh Veeramacheneni, Moritz Wolter, Hilde Kuehne et al.

ICLR 2025posterarXiv:2312.15289
13
citations

FreDF: Learning to Forecast in the Frequency Domain

Hao Wang, Lichen Pan, Yuan Shen et al.

ICLR 2025posterarXiv:2402.02399
63
citations

FreeCG: Free the Design Space of Clebsch-Gordan Transform for Machine Learning Force Fields

Shihao Shao, Haoran Geng, Zun Wang et al.

ICLR 2025posterarXiv:2407.02263