collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2025

Lucy: edgerunning agentic web search on mobile with machine generated task vectors

Alan Dao, Dinh Bach Vu, Alex Nguyen +1

Small language models (SLMs) are inherently limited in knowledge-intensive tasks due to their constrained capacity. While test-time computation offers a path to enhanced performanc…

cs.CL2025

Jan-nano Technical Report

Alan Dao, Dinh Bach Vu

Most language models face a fundamental tradeoff where powerful capabilities require substantial computational resources. We shatter this constraint with Jan-nano, a 4B parameter l…

cs.CL2025

ReZero: Enhancing LLM search ability by trying one-more-time

Alan Dao, Thinh Le

Retrieval-Augmented Generation (RAG) improves Large Language Model (LLM) performance on knowledge-intensive tasks but depends heavily on initial search query quality. Current metho…

cs.CL2025

Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant

Alan Dao, Dinh Bach Vu, Huy Hoang Ha

Large Language Models (LLMs) have revolutionized natural language processing, but their application to speech-based tasks remains challenging due to the complexities of integrating…

cs.CL2025

AlphaSpace: Enabling Robotic Actions through Semantic Tokenization and Symbolic Reasoning

Alan Dao, Dinh Bach Vu, Bui Quang Huy

This paper presents AlphaSpace, a novel methodology designed to enhance the spatial reasoning capabilities of language models for robotic manipulation in 3D Cartesian space. AlphaS…

cs.CL2025

AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO

Alan Dao, Dinh Bach Vu

Large Language Models (LLMs) have demonstrated impressive capabilities in language processing, yet they often struggle with tasks requiring genuine visual spatial reasoning. In thi…