17 citations · 60 across the 30 of their papers we have counts for
30 papers
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
NeoHorse Team, Guoliang Cao, Guohao Dai +34
Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into the next round of learning. We p…
Agentic Routing: The Harness-Native Data Flywheel
Xinchen Liu, Hang Zhou, Yingjie Zong +12
Large language model agents are increasingly executed not by a single model call, but by an execution harness that manages observation, context, control, action, state, and verific…
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Mengyu Zheng, Kai Han, Boxun Li +13
The software engineering capabilities of general-purpose agent harnesses remain underexplored, and existing benchmarks offer limited support for comparing these harnesses under con…
PocketLLM: Ultimate Compression of Large Language Models via Meta Networks
Ye Tian, Chengcheng Wang, Jing Han +2
As Large Language Models (LLMs) continue to grow in size, storing and transmitting them on edge devices becomes increasingly challenging. Traditional methods like quantization and…
ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters
Zhiwei Hao, Jianyuan Guo, Li Shen +4
Recent advancements in vision transformers (ViTs) have demonstrated that larger models often achieve superior performance. However, training these models remains computationally in…
LLM Data Selection and Utilization via Dynamic Bi-level Optimization
Yang Yu, Kai Han, Hang Zhou +4
While large-scale training data is fundamental for developing capable large language models (LLMs), strategically selecting high-quality data has emerged as a critical approach to…
EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware Optimization
Zhongqian Fu, Tianyi Zhao, Ning Ding +4
Mixture-of-Experts (MoE) models enable scalable computation and performance in large-scale deep learning but face quantization challenges due to sparse expert activation and dynami…
Transferable text data distillation by trajectory matching
Rong Yao, Hailin Hu, Yifei Fu +5
In the realm of large language model (LLM), as the size of large models increases, it also brings higher training costs. There is a urgent need to minimize the data size in LLM tra…
Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping
Ning Ding, Jing Han, Yuchuan Tian +3
Diffusion Transformer (DiT) has now become the preferred choice for building image generation models due to its great generation capability. Unlike previous convolution-based UNet…
SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs
Shibo Jie, Yehui Tang, Kai Han +2
Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the…
Mixture of Lookup Experts
Shibo Jie, Yehui Tang, Kai Han +4
Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up.…
Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning
Hang Zhou, Yehui Tang, Haochen Qin +5
The efficacy of large language models (LLMs) on downstream tasks usually hinges on instruction tuning, which relies critically on the quality of training data. Unfortunately, colle…
MemoryFormer: Minimize Transformer Computation by Removing Fully-Connected Layers
Ning Ding, Yehui Tang, Haochen Qin +6
In order to reduce the computational complexity of large language models, great efforts have been made to to improve the efficiency of transformer models such as linear attention a…
Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs
Kai Han, Jianyuan Guo, Yehui Tang +3
Vision-language large models have achieved remarkable success in various multi-modal tasks, yet applying them to video understanding remains challenging due to the inherent complex…
Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning
Shibo Jie, Yehui Tang, Jianyuan Guo +3
Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, e.g., pruning inattentive tokens or merging sim…
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
Ding Jia, Jianyuan Guo, Kai Han +4
Cross-modal transformers have demonstrated superiority in various vision tasks by effectively integrating different modalities. This paper first critiques prior token exchange meth…
Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
Shibo Jie, Yehui Tang, Ning Ding +3
Current solutions for efficiently constructing large vision-language (VL) models follow a two-step paradigm: projecting the output of pre-trained vision encoders to the input space…
EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models
Yunsheng Ni, Chuanjian Liu, Yehui Tang +2
Speculative decoding emerges as a pivotal technique for enhancing the inference speed of Large Language Models (LLMs). Despite recent research aiming to improve prediction efficien…
Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting
Fangcheng Liu, Yehui Tang, Zhenhua Liu +3
Speculative decoding has demonstrated its effectiveness in accelerating the inference of large language models while maintaining a consistent sampling distribution. However, the co…
GhostNetV3: Exploring the Training Strategies for Compact Models
Zhenhua Liu, Zhiwei Hao, Kai Han +2
Compact neural networks are specially designed for applications on edge devices with faster inference speed yet modest performance. However, training strategies of compact models a…
DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models
Wei He, Kai Han, Yehui Tang +4
Large language models (LLMs) face a daunting challenge due to the excessive computational and memory requirements of the commonly used Transformer architecture. While state space m…
A robust audio deepfake detection system via multi-view feature
Yujie Yang, Haochen Qin, Hang Zhou +4
With the advancement of generative modeling techniques, synthetic human speech becomes increasingly indistinguishable from real, and tricky challenges are elicited for the audio de…
Data-efficient Large Vision Models through Sequential Autoregression
Jianyuan Guo, Zhiwei Hao, Chengcheng Wang +5
Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding. These models are intended…
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Jianyuan Guo, Hanting Chen, Chengcheng Wang +3
Recent advancements in large language models have sparked interest in their extraordinary and near-superhuman capabilities, leading researchers to explore methods for evaluating an…