activity
20242026
collaborators

13 papers

cs.LG2026

Quantized Reasoning Models Think They Need to Think Longer, but They Do Not

Sanae Lotfi, Polina Kirichenko, Steven Li +1

Post-training quantization (PTQ) is widely used to deploy large language models efficiently, but its effect on reasoning models is not well understood. Across math, coding, and sci…

cs.CV2026

VLM3: Vision Language Models Are Native 3D Learners

Zhipeng Cai, Zhuang Liu, Yunyang Xiong +3

Vision Language Models (VLMs) enable a unified model to solve various vision tasks through prompting. They have shown promising performance in semantic understanding. However, 3D u…

cs.LG2026

MobileMoE: Scaling On-Device Mixture of Experts

Yanbei Chen, Hanxian Huang, Ernie Chang +5

Mixture-of-Experts (MoE) has become the de facto architecture for hundred-billion-parameter language models, yet its advantages at sub-billion scales for on-device deployment remai…

cs.LG2026

WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points

Dongyue Li, Zechun Liu, Kai Yi +6

Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized model. The main bottleneck is…

cs.LG2026

MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment

Hanxian Huang, Igor Fedorov, Andrey Gromov +14

Real-time AI experiences call for on-device large language models (OD-LLMs) optimized for efficient deployment on resource-constrained hardware. The most useful OD-LLMs produce nea…

cs.LG2026

Neural Computers

Mingchen Zhuge, Changsheng Zhao, Haozhe Liu +16

We propose a new frontier: Neural Computers (NCs) that unify computation, memory, and I/O of traditional computers in a learned runtime state. Our long-term goal is the Completely…