Self-Hinting Language Models Enhance Reinforcement Learning Paper • 2602.03143 • Published Feb 3 • 31
3rd Place Report of LSVOS 2025 MeViS Track: Sa2VA-i: Improving Sa2VA Results with Consistent Training and Inference Paper • 2509.19082 • Published Sep 23, 2025 • 1
Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning Paper • 2306.00477 • Published Jun 1, 2023 • 2
Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token Paper • 2211.04898 • Published Nov 9, 2022
3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability Paper • 2409.00119 • Published Aug 28, 2024 • 1
Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation Paper • 2505.06027 • Published May 9, 2025 • 18
Reward-Guided Speculative Decoding for Efficient LLM Reasoning Paper • 2501.19324 • Published Jan 31, 2025 • 39
UGainS: Uncertainty Guided Anomaly Instance Segmentation Paper • 2308.02046 • Published Aug 3, 2023 • 1
Mask4Former: Mask Transformer for 4D Panoptic Segmentation Paper • 2309.16133 • Published Sep 28, 2023 • 1
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think Paper • 2409.11355 • Published Sep 17, 2024 • 31
InstrumentGen: Generating Sample-Based Musical Instruments From Text Paper • 2311.04339 • Published Nov 7, 2023
Distortion Audio Effects: Learning How to Recover the Clean Signal Paper • 2202.01664 • Published Feb 3, 2022
Generating Sample-Based Musical Instruments Using Neural Audio Codec Language Models Paper • 2407.15641 • Published Jul 22, 2024