1 citations · 2 across the 13 of their papers we have counts for
15 papers
From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG
Zlatan Feric, Amir Taherin, Yanzhi Wang +1
Retrieval-augmented generation (RAG) improves language-model responses by grounding generation in external passages, which comes with overhead: retrieved context lengthens the prom…
Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B
Rahul Chowdhury, Timothy A Rupprecht, Senhao Cao +5
Recent work has shown that large language models (LLMs) exhibit strong numerical sequence modeling capabilities and show promise in time-series prediction. While LLMs display in-co…
Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT
Pu Zhao, Changdi Yang, Yixiao Chen +4
Translating C code into safe, idiomatic Rust is a longstanding software-engineering goal because it can eliminate entire classes of memory-safety vulnerabilities while preserving t…
ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision Language Models
Rahul Chowdhury, Timothy A Rupprecht, Xuan Shen +2
Spatial reasoning remains a persistent challenge for many vision language models (VLMs), and improving it typically requires fine-tuning with substantial additional parameters. Our…
PhyGround: Benchmarking Physical Reasoning in Generative World Models
Juyi Lin, Arash Akbari, Yumei He +13
Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern real-world dynamics. However, ev…
CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs
Shiyang Li, Zijian Zhang, Guangyan Sun +5
Large language models show promise for automated CUDA programming, however even the strongest coding models (e.g., Claude-Opus-4.6) may still fall short of expert-level, architectu…
Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density
Zhendong Mi, Yixiao Chen, Pu Zhao +4
Mixture-of-Experts (MoE) based Large Language Models (LLMs) have achieved superior performance, yet the massive memory overhead caused by storing multiple expert networks severely…
Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA
Pu Zhao, Arash Akbari, Xuan Shen +16
Recently, Large Language Models (LLMs) have undergone a significant transformation, marked by a rapid rise in both their popularity and capabilities. Leading this evolution are pro…
Collaborative Compression for Large-Scale MoE Deployment on Edge
Yixiao Chen, Yanyue Xie, Ruining Yang +6
The Mixture of Experts (MoE) architecture is an important method for scaling Large Language Models (LLMs). It increases model capacity while keeping computation cost low. However,…
RAGs to Riches: RAG-like Few-shot Learning for Large Language Model Role-playing
Timothy Rupprecht, Enfu Nan, Arash Akbari +8
Role-playing Large language models (LLMs) are increasingly deployed in high-stakes domains such as healthcare, education, and governance, where failures can directly impact user tr…
Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs
Amir Taherin, Juyi Lin, Arash Akbari +5
Vision-Language-Action (VLA) models have emerged as powerful generalist policies for robotic control, yet their performance scaling across model architectures and hardware platform…
VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting
Juyi Lin, Amir Taherin, Arash Akbari +11
Recent large-scale Vision Language Action (VLA) models have shown superior performance in robotic manipulation tasks guided by natural language. However, current VLA models suffer…
Verbal Werewolf: Engage Users with Verbalized Agentic Werewolf Game Framework
Qihui Fan, Wenbo Li, Enfu Nan +4
The growing popularity of social deduction games has created an increasing need for intelligent frameworks where humans can collaborate with AI agents, particularly in post-pandemi…
7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement
Pu Zhao, Xuan Shen, Zhenglun Kong +16
Recently, Large Language Models (LLMs) have undergone a significant transformation, marked by a rapid rise in both their popularity and capabilities. Leading this evolution are pro…
Digital Avatars: Framework Development and Their Evaluation
Timothy Rupprecht, Sung-En Chang, Yushu Wu +9
We present a novel prompting strategy for artificial intelligence driven digital avatars. To better quantify how our prompting strategy affects anthropomorphic features like humor,…