OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer
Comments Accepted by ICLR 2025
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks
Comments 35 pages; 9 figures; accepted at the International Conference on Learning Representations (ICLR)
Accelerated Training through Iterative Gradient Propagation Along the Residual Path
Comments 20 pages, 6 figures, accepted to ICLR 2025
Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models
Comments Published as a conference paper at ICLR 2025. The model is available at https://huggingface.co/StevenHH2000/Finedefics
Accelerating Task Generalisation with Multi-Level Skill Hierarchies
Comments 10 pages, accepted at ICLR 2025
TODO: Enhancing LLM Alignment with Ternary Preferences
Comments Accepted to ICLR 2025
Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation
Comments ICLR 2025
MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
Comments ICLR 2025 Oral
DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL
Comments ICLR'25 (Oral)
ToolGen: Unified Tool Retrieval and Calling via Generation
Comments ICLR 2025
Learning 3D Perception from Others' Predictions
Comments Accepted to ICLR 2025
Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models
Comments This paper has been accepted to ICLR 2025
Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning
Comments Accepted to ICLR 2025
Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates
Comments Accepted by Building Trust in LLMs and LLM Applications workshop at ICLR 2025
Blind Baselines Beat Membership Inference Attacks for Foundation Models
Comments Accepted to be presented at DATA-FM @ ICLR 2025 and IEEE DLSP Workshop 2025
Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation
Comments Accepted to ICLR 2025
Nepotistically Trained Generative-AI Models Collapse
Journal ref Published in ICLR DATA-FM Workshop, 2025
Semantix: An Energy Guided Sampler for Semantic Style Transfer
Comments 28 pages, 19 figures, Accepted to ICLR 2025
A Proposal for Networks Capable of Continual Learning
Comments Published at ICLR 2025 World Models Workshop
UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models
Comments This work has been accepted for publication at the International Conference on Learning Representations (ICLR) 2025
FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking
Comments Accepted in ICLR 2025
Frame-Voyager: Learning to Query Frames for Video Large Language Models
Comments ICLR 2025, Camera-ready Version
Empirical Asset Pricing with Large Language Model Agents
Comments ICLR 2025 Workshop on Advances in Financial AI
Population Transformer: Learning Population-level Representations of Neural Activity
Comments ICLR 2025, Project page https://glchau.github.io/population-transformer/
HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark
Comments Accepted at ICLR 2021 (Spotlight)
Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement
Comments Accepted by ICLR 2025
Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
Comments Accepted to ICLR 2025
Model Assembly Learning with Heterogeneous Layer Weight Merging
Comments ICLR 2025 Workshop on Neural Network Weights as a New Data Modality
Unveiling the Potential of Superexpressive Networks in Implicit Neural Representations
Comments Accepted at ICLR 2025 Workshop on Neural Network Weights as a New Data Modality
LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models
Comments ICLR 2025 Workshop at SCOPE (Oral), 16 pages, 5 figures, short paper (6 pages exclude reference and appendix)
