Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness
Comments 20 pages, ICLR 2025
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages
Comments ICLR 2025
Quantized Spike-driven Transformer
Comments Accepted by ICLR 2025
Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms
Journal ref Proceedings of the 13th International Conference on Learning Representations (ICLR), 2025
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
Comments Accepted by ICLR for a spotlight presentation
Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification
Comments ICLR 2025 camera ready
Linear Partial Gromov-Wasserstein Embedding
Comments Published at ICLR 2025
BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping
Comments Published at ICLR 2025
Enhancing Startup Success Predictions in Venture Capital: A GraphRAG Augmented Multivariate Time Series Method
Comments ICLR 2025 Financial AI
LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
Comments Camera-Ready Version for ICLR 2025; technical corrections to previous version
VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
Comments ICLR 2025; Project Page: https://snap-research.github.io/vd3d/
Expressivity of Neural Networks with Random Weights and Learned Biases
Comments upload of camera-ready manuscript accepted as poster at ICLR 2025; change of author order
Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization
Comments ICLR 2025 Spotlight
Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View
Comments Published as a conference paper at ICLR 2025
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
Comments ICLR 2024 camera-ready; Code is located at https://github.com/angie-chen55/sudden-drops-in-the-loss/tree/main
Exploring a Principled Framework for Deep Subspace Clustering
Comments The paper is accepted by ICLR 2025. The first two authors are equally contributed
AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution
Comments 24 pages, 11 figures, ICLR 2025
TopoDiffusionNet: A Topology-aware Diffusion Model
Comments Accepted to ICLR 2025 (Poster)
URLOST: Unsupervised Representation Learning without Stationarity or Topology
Comments Accepted by ICLR 2025; Code will be available at this https://github.com/zeyuyun1/URLOST
Structure Is Not Enough: Leveraging Behavior for Neural Network Weight Reconstruction
Comments Accepted at the ICLR Workshop on Neural Network Weights as a New Data Modality 2025
Causally Aligned Curriculum Learning
Comments Accepted as Posters in ICLR 2024
Think-Then-React: Towards Unconstrained Human Action-to-Reaction Generation
Comments Accepted by ICLR 2025
Strength Estimation and Human-Like Strength Adjustment in Games
Comments Accepted by the Thirteenth International Conference on Learning Representations (ICLR 2025)
OptionZero: Planning with Learned Options
Comments Accepted by the Thirteenth International Conference on Learning Representations (ICLR 2025) as oral presentation
Sparse autoencoders reveal selective remapping of visual concepts during adaptation
Comments Published as a conference paper at the Thirteenth International Conference on Learning Representations (ICLR 2025)
Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification
Comments Accepted to ICLR 2025. Code is available at https://github.com/Osilly/dynamic_llava
Catastrophic Failure of LLM Unlearning via Quantization
Comments ICLR 2025
JPEG Inspired Deep Learning
Journal ref The Thirteenth International Conference on Learning Representations 2025 (ICLR 2025)
Near Exact Privacy Amplification for Matrix Mechanisms
Comments To appear in ICLR 2025
Selective Aggregation for Low-Rank Adaptation in Federated Learning
Comments Accepted at ICLR 2025
