papers

Publications (14)

cs.AR2023

OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization

Cong Guo, Jiaming Tang, Weiming Hu +6

Transformer-based large language models (LLMs) have achieved great success with the growing model size. LLMs' size grows by every two years, which outpaces the hardware…

cs.CL2024

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Guangxuan Xiao, Jiaming Tang, Jingwei Zuo +5

Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. Caching all Key and Value (KV) states across all attenti…

cs.CL2026

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Ji Lin, Jiaming Tang, Haotian Tang +7

Large language models (LLMs) have transformed numerous AI applications. On-device LLM is becoming increasingly important: running LLMs locally on edge devices can reduce the cloud…

cs.AR2025

Transitive Array: An Efficient GEMM Accelerator with Result Reuse

Cong Guo, Chiyue Wei, Jiaming Tang +4

Deep Neural Networks (DNNs) and Large Language Models (LLMs) have revolutionized artificial intelligence, yet their deployment faces significant memory and computational challenges…

cs.LG2025

Twilight: Adaptive Attention Sparsity with Hierarchical Top- Pruning

Chaofan Lin, Jiaming Tang, Shuo Yang +6

Leveraging attention sparsity to accelerate long-context large language models (LLMs) has been a hot research topic. However, current algorithms such as sparse attention or key-val…

cs.CL2024

Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Jiaming Tang, Yilong Zhao, Kan Zhu +3

As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-con…

cs.RO2025

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference

Jiaming Tang, Yufei Sun, Yilong Zhao +7

Vision-Language-Action models (VLAs) are becoming increasingly capable across diverse robotic tasks. However, these models are typically deployed under synchronous inference, where…

cs.LG2024

DCRMTA: Unbiased Causal Representation for Multi-touch Attribution

Jiaming Tang

Multi-touch attribution (MTA) currently plays a pivotal role in achieving a fair estimation of the contributions of each advertising touchpoint to-wards conversion behavior, deeply…

cs.LG2025

Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding

Yilong Zhao, Jiaming Tang, Kan Zhu +10

Reasoning language models have demonstrated remarkable capabilities on challenging tasks by generating elaborate chain-of-thought (CoT) solutions. However, such lengthy generation…

cs.LG2026

: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities

Physical Intelligence, Bo Ai, Ali Amin +85

We present a new robotic foundation model, called , that can enable strong out-of-the-box performance in a wide range of scenarios. can follow diverse language…

cs.AI2025

AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systems

Yun Piao, Hongbo Min, Hang Su +28

The rapid advancement of Large Language Models (LLMs) is catalyzing a shift towards autonomous AI Agents capable of executing complex, multi-step tasks. However, these agents remai…

cs.CL2025

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

Shang Yang, Junxian Guo, Haotian Tang +7

Large language models (LLMs) have shown remarkable potential in processing long sequences and complex reasoning tasks, yet efficiently serving these models remains challenging due…

cs.CV2025

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference

Samir Khaki, Junxian Guo, Jiaming Tang +6

Vision Language Models (VLMs) have rapidly advanced in integrating visual and textual reasoning, powering applications across high-resolution image understanding, long-video analys…

cs.RO2026

MEM: Multi-Scale Embodied Memory for Vision Language Action Models

Marcel Torne, Karl Pertsch, Homer Walke +14

Conventionally, memory in end-to-end robotic learning involves inputting a sequence of past observations into the learned policy. However, in complex multi-stage real-world tasks,…