Jiaming Tang

activity

20242026

most citedAWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

75 citations · 75 across the 1 of their papers we have counts for

collaborators

Showing cs.LGShow all

3 papers · 1 filter

cs.LG2026

$I ¨ _{0.7}$ : a Steerable Generalist Robotic Foundation Model with Emergent Capabilities

Physical Intelligence, Bo Ai, Ali Amin +85

We present a new robotic foundation model, called $I ¨ _{0.7}$ , that can enable strong out-of-the-box performance in a wide range of scenarios. $I ¨ _{0.7}$ can follow diverse language…

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.LG2025

Twilight: Adaptive Attention Sparsity with Hierarchical Top- $p$ 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…

I¨0.7​: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities

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

Twilight: Adaptive Attention Sparsity with Hierarchical Top-p Pruning

$I ¨ _{0.7}$ : a Steerable Generalist Robotic Foundation Model with Emergent Capabilities

Twilight: Adaptive Attention Sparsity with Hierarchical Top- $p$ Pruning