Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
Comments Spotlight at NeurIPS 2024 D&B Track. 32 pages, 18 figures, Project Page: https://lpercc.github.io/HA3D_simulator/
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis
Comments NeurIPS'24 Spotlight
A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression
Comments This is an extended version of a paper published in the proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024); this version was presented at the 4th NeurIPS Workshop on Efficient Natural Language and Speech Processing (ENLSP-IV)
Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning
Comments Accepted at NeurIPS 2024. 49 pages, 13 figures, Project: https://github.com/ZebangCheng/Emotion-LLaMA, Demo: https://huggingface.co/spaces/ZebangCheng/Emotion-LLaMA
Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses
Comments NeurIPS 2024
Protein-Nucleic Acid Complex Modeling with Frame Averaging Transformer
Comments Accepted at NeurIPS 2024
Why Warmup the Learning Rate? Underlying Mechanisms and Improvements
Comments Accepted at NeurIPS 2024 (camera-ready version). Updates: (1) self-stabilization model for warmup mechanisms added, (2) introduced Flat Adam optimizer, (3) additional results for language modeling results and comparison to RAdam
IllumiNeRF: 3D Relighting Without Inverse Rendering
Comments NeurIPS 2024; v2 (for camera-ready) added single-GPU results and discussions on Stanford-ORB illuminations; Project page: https://illuminerf.github.io/
How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
Comments To appear in NeurIPS 2024
Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data
Comments 30 pages, 4 figures, NeurIPS 2024
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
Comments NeurIPS 2024 Datasets and Benchmarks Track
CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark
Comments 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks
Aligning Large Language Models with Representation Editing: A Control Perspective
Comments NeurIPS 2024
Learning to Edit Visual Programs with Self-Supervision
Comments Neurips 2024
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
Comments Published as a conference paper at NeurIPS 2024
An Equivalence Between Static and Dynamic Regret Minimization
Comments 36 pages; v2: NeurIPS 2024
Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation
Comments NeurIPS 2024 oral
Compressing Large Language Models using Low Rank and Low Precision Decomposition
Comments Accepted to The 38th Conference on Neural Information Processing Systems (NeurIPS 2024). [31 pages, 10 figures, 9 tables]
Why are Visually-Grounded Language Models Bad at Image Classification?
Comments Published at NeurIPS 2024
A Canonicalization Perspective on Invariant and Equivariant Learning
Comments In Thirty-eighth Conference on Neural Information Processing Systems (2024)
Frustratingly Easy Test-Time Adaptation of Vision-Language Models
Comments Camera-ready version for NeurIPS 2024
InversionView: A General-Purpose Method for Reading Information from Neural Activations
Comments NeurIPS 2024; ICML 2024 Mechanistic Interpretability Workshop oral
Learning to Reason via Program Generation, Emulation, and Search
Comments NeurIPS 2024 camera ready
M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation
Comments Accepted at NeurIPS 2024, 21 pages, 7 figures
A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis
Comments Published in NeurIPS 2024 (Spotlight), project page: https://yueyang1996.github.io/knobo/
SimPO: Simple Preference Optimization with a Reference-Free Reward
Comments NeurIPS 2024. Code & models: https://github.com/princeton-nlp/SimPO. v3 updates: Gemma 2 results (Appendix J); more discussions about length normalization (Section 2.2) and KL regularization (Section 2.3)
Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast
Comments NeurIPS 2024
Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
Comments Accepted at NeurIPS 2024 (camera-ready version)
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
Comments To appear in the Proceedings of the Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024). Please cite accordingly
Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
Comments Accepted to NeurIPS 2024, 26 pages
