Speechless: Speech Instruction Training Without Speech for Low Resource Languages Paper β’ 2505.17417 β’ Published May 23 β’ 14
VoxRep: Enhancing 3D Spatial Understanding in 2D Vision-Language Models via Voxel Representation Paper β’ 2503.21214 β’ Published Mar 27 β’ 2
ReZero: Enhancing LLM search ability by trying one-more-time Paper β’ 2504.11001 β’ Published Apr 15 β’ 16
AlphaSpace: Enabling Robotic Actions through Semantic Tokenization and Symbolic Reasoning Paper β’ 2503.18769 β’ Published Mar 24 β’ 11
PoseLess: Depth-Free Vision-to-Joint Control via Direct Image Mapping with VLM Paper β’ 2503.07111 β’ Published Mar 10 β’ 3
AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO Paper β’ 2502.14669 β’ Published Feb 20 β’ 15
Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant Paper β’ 2410.15316 β’ Published Oct 20, 2024 β’ 12
π Ichigo v0.3 Collection The experimental family designed to train LLMs to understand sound natively. β’ 6 items β’ Updated Nov 11, 2024 β’ 18
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding Paper β’ 2404.16710 β’ Published Apr 25, 2024 β’ 80
LLM Hallucination Detection Papers Collection Collection of LLM hallucination and evaluation papers that I've been exploring and implementing. Some of them have my comments and annotated doodles. β’ 12 items β’ Updated Feb 20, 2024 β’ 13