ICLR 2025 Workshop SCOPE Submissions

Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models
Andy Zhou, Ron Arel
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts
Weigao Sun, Disen Lan, Tong Zhu, Xiaoye Qu, Yu Cheng
- Published: 05 Mar 2025, Last Modified: 15 Apr 2025
- SCOPE - ICLR 2025 Oral
- Readers: Everyone
Margin-aware Preference Optimization for Aligning Diffusion Models without Reference
Jiwoo Hong, Sayak Paul, Noah Lee, Kashif Rasul, James Thorne, Jongheon Jeong
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
STIV: SCALABLE TEXT AND IMAGE CONDITIONED VIDEO GENERATION
Zongyu Lin, Wei Liu, Chen Chen, Jiasen Lu, Wenze Hu, Tsu-Jui Fu, Jesse Allardice, Zhengfeng Lai, Liangchen Song, Bowen Zhang, cha chen, Yiran Fei, Yifan Jiang, Lezhi Li, Yizhou Sun, Kai-Wei Chang, Yinfei Yang
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Oral
- Readers: Everyone
The Curse of Depth in Large Language Models
Wenfang Sun, Xinyuan Song, Pengxiang Li, Lu Yin, Yefeng Zheng, Shiwei Liu
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs
Zhen Tan, Daize Dong, Xinyu Zhao, Jianing Cai, Jie Peng, Yu Cheng, Tianlong Chen
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
QMambaExtend: Improving Long-Context Extension of Memory-Efficient Mamba Models
Seyedarmin Azizi, Souvik Kundu, Mohammad Erfan Sadeghi, Massoud Pedram
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
Overtrained Language Models Are Harder to Fine-Tune
Jacob Mitchell Springer, Sachin Goyal, Kaiyue Wen, Tanishq Kumar, Xiang Yue, Sadhika Malladi, Graham Neubig, Aditi Raghunathan
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Oral
- Readers: Everyone
LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models
Sihwan Park, Doohyuk Jang, Sung-Yub Kim, Souvik Kundu, Eunho Yang
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Oral
- Readers: Everyone
Efficient Open-set Test Time Adaptation of Vision Language Models
Manogna Sreenivas, Soma Biswas
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
Effortless Efficiency: Low-Cost Pruning of Diffusion Models
Yang Zhang, Er Jin, Yanfei Dong, Ashkan Khakzar, Philip Torr, Johannes Stegmaier, Kenji Kawaguchi
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
Stable-SPAM: How to Train in 4-Bit More Stably than 16-Bit Adam
Tianjin Huang, Haotian Hu, Zhenyu Zhang, Gaojie Jin, Xiang Li, Li Shen, Tianlong Chen, Lu Liu, Qingsong Wen, Zhangyang Wang, Shiwei Liu
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
SPAM: SPIKE-AWARE ADAM WITH MOMENTUM RESET FOR STABLE LLM TRAINING
Tianjin Huang, Ziquan Zhu, Gaojie Jin, Lu Liu, Zhangyang Wang, Shiwei Liu
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
Revisiting Associative Recall in Modern Recurrent Models
Destiny Okpekpe, Antonio Orvieto
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
PENCIL: Long Thoughts with Short Memory
Chenxiao Yang, Nathan Srebro, David McAllester, Zhiyuan Li
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
Universal LLM Routing with Correctness-Based Representation
Wittawat Jitkrittum, Harikrishna Narasimhan, Ankit Singh Rawat, Jeevesh Juneja, Zifeng Wang, Chen-Yu Lee, Pradeep Shenoy, Rina Panigrahy, Aditya Krishna Menon, Sanjiv Kumar
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
AsymLoRA: Unlocking the Power of Multimodal LLMs via Asymmetric LoRA
Xuyang Wei, Chunlin Tian, Li Li
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
Acceleration Multiple Heads Decoding for LLM via Dynamic Tree Attention
Zhendong Zhang
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2
Steven Abreu, Sumit Bam Shrestha, Rui-Jie Zhu, Jason Eshraghian
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
Graph Low-Rank Adapters of High Regularity for Graph Neural Networks and Graph Transformers
Pantelis Papageorgiou, Haitz Sáez de Ocáriz Borde, Anastasis Kratsios, Michael M. Bronstein
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals
Utkarsh Saxena, Sayeh Sharify, Kaushik Roy, Xin Wang
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Oral
- Readers: Everyone
MixER: Better Mixture of Experts Routing for Hierarchical Meta-Learning
Roussel Desmond Nzoyem, Grant Stevens, Amarpal Sahota, David A.W. Barton, Tom Deakin
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
Adaptive Length Image Tokenization via Recurrent Allocation
Shivam Duggal, Phillip Isola, Antonio Torralba, William T. Freeman
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
Fixed-Point RNNs: From Diagonal to Dense in a Few Iterations
Sajad Movahedi, Felix Sarnthein, Nicola Muca Cirone, Antonio Orvieto
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone
Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking
Will LeVine, Bijan Varjavand
- Published: 05 Mar 2025, Last Modified: 14 Apr 2025
- SCOPE - ICLR 2025 Poster
- Readers: Everyone