13 citations · 49 across the 39 of their papers we have counts for
15 papers · 1 filter
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Chujie Zheng, Kai Dang, Bowen Yu +10
This paper proposes a novel formulation for reinforcement learning (RL) with large language models, explaining why and under what conditions the true sequence-level reward can be o…
MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training
Wenxuan Li, Chengruidong Zhang, Huiqiang Jiang +3
The adoption of long context windows has become a standard feature in Large Language Models (LLMs), as extended contexts significantly enhance their capacity for complex reasoning…
Scaling LLM Test-Time Compute with Mobile NPU on Smartphones
Zixu Hao, Jianyu Wei, Tuowei Wang +5
Deploying Large Language Models (LLMs) on mobile devices faces the challenge of insufficient performance in smaller models and excessive resource consumption in larger ones. This p…
Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning
Shaobo Wang, Jiaming Wang, Jiajun Zhang +9
As supervised fine-tuning (SFT) evolves from a lightweight post-training step into a compute-intensive phase rivaling mid-training in scale, data efficiency has become critical for…
LeanK: Learnable K Cache Channel Pruning for Efficient Decoding
Yike Zhang, Zhiyuan He, Huiqiang Jiang +4
Large language models (LLMs) enable long-context tasks but face efficiency challenges due to the growing key-value (KV) cache. We propose LeanK, a learning-based method that prunes…
Accelerating Prefilling via Decoding-time Contribution Sparsity
Zhiyuan He, Yike Zhang, Chengruidong Zhang +3
Large Language Models (LLMs) incur quadratic attention complexity with input length, creating a major time bottleneck in the prefilling stage. Existing acceleration methods largely…
SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression
Yucheng Li, Surin Ahn, Huiqiang Jiang +3
Large language models (LLMs) have achieved widespread adoption across numerous applications. However, many LLMs are vulnerable to malicious attacks even after safety alignment. The…
GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
Qianhui Wu, Kanzhi Cheng, Rui Yang +15
One of the principal challenges in building VLM-powered GUI agents is visual grounding, i.e., localizing the appropriate screen region for action execution based on both the visual…
Chain-of-Model Learning for Language Model
Kaitao Song, Xiaohua Wang, Xu Tan +14
In this paper, we propose a novel learning paradigm, termed Chain-of-Model (CoM), which incorporates the causal relationship into the hidden states of each layer as a chain style,…
MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention
Yucheng Li, Huiqiang Jiang, Chengruidong Zhang +8
The integration of long-context capabilities with visual understanding unlocks unprecedented potential for Vision Language Models (VLMs). However, the quadratic attention complexit…
RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference
Yaoqi Chen, Jinkai Zhang, Baotong Lu +16
Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because t…
Zoomer: Adaptive Image Focus Optimization for Black-box MLLM
Jiaxu Qian, Chendong Wang, Yifan Yang +16
Multimodal large language models (MLLMs) such as GPT-4o, Gemini Pro, and Claude 3.5 have enabled unified reasoning over text and visual inputs, yet they often hallucinate in real w…
Scaling Up On-Device LLMs via Active-Weight Swapping Between DRAM and Flash
Fucheng Jia, Zewen Wu, Shiqi Jiang +7
Large language models (LLMs) are increasingly being deployed on mobile devices, but the limited DRAM capacity constrains the deployable model size. This paper introduces ActiveFlow…
On Memory Construction and Retrieval for Personalized Conversational Agents
Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang +8
To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory ba…
xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction
Chi-Chih Chang, Wei-Cheng Lin, Chien-Yu Lin +8
Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent studies attempt to share KV-Cache…