OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation
Comments Accepted to ICLR 2025; Project page: https://wgsxm.github.io/projects/omniphysgs/
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
STAMP: Scalable Task And Model-agnostic Collaborative Perception
Comments Paper is accepted by ICLR 2025
Provable Weak-to-Strong Generalization via Benign Overfitting
Comments ICLR 2025, 38 pages, 4 figures
MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks
Comments Accepted at ICLR 2025
Inverse decision-making using neural amortized Bayesian actors
Comments published as a conference paper at ICLR 2025
BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models
Comments ICLR 2025
Idempotence and Perceptual Image Compression
Comments ICLR 2024
Track-On: Transformer-based Online Point Tracking with Memory
Comments ICLR 2025
Sebra: Debiasing Through Self-Guided Bias Ranking
Comments Accepted to ICLR 2025
Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio Test
Comments Accepted to International Conference on Learning Representations (ICLR) 2025
Provence: efficient and robust context pruning for retrieval-augmented generation
Comments Accepted to ICLR 2025
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
Comments ICLR 2025
Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning
Comments Published in The Thirteenth International Conference on Learning Representations (ICLR) 2025. The first two authors contributed equally
Collapsed Language Models Promote Fairness
Comments ICLR 2025
General Scene Adaptation for Vision-and-Language Navigation
Comments ICLR 2025
Breaking the $\log(1/Δ_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids
Comments 21 pages, published at ICLR 2025
PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding
Comments ICLR 2025. Project page: https://physbench.github.io/ Dataset: https://huggingface.co/datasets/USC-GVL/PhysBench
Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
Comments International Conference on Learning Representations (ICLR 2025)
CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation
Comments Accepted at ICLR 2025
DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation
Comments Accepted to ICLR 2025; Project page: https://chenguolin.github.io/projects/DiffSplat
CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
Comments Accepted by ICLR 2025
SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments
Comments 27 pages, accepted to ICLR 2025
DynaPrompt: Dynamic Test-Time Prompt Tuning
Comments ICLR 2025
Horizon Generalization in Reinforcement Learning
Journal ref International Conference on Learning Representations (ICLR), 2025
Reinforcement Learning for Control of Non-Markovian Cellular Population Dynamics
Comments Accepted at ICLR 2025
Can Watermarked LLMs be Identified by Users via Crafted Prompts?
Comments 28 pages, 5 figures, 11 tables Published as a conference paper at ICLR 2025 Github link: https://github.com/THU-BPM/Watermarked_LLM_Identification
Towards General-Purpose Model-Free Reinforcement Learning
Comments ICLR 2025
Universal Image Restoration Pre-training via Degradation Classification
Comments Accepted by ICLR 2025
Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection
Comments Accepted at the 13th International Conference on Learning Representations (ICLR) 2025
Group Ligands Docking to Protein Pockets
Comments 18 pages, published in ICLR 2025
