Search Results for author:
Found 23 papers, 8 papers with code
EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices
Transformer-based large language models (LLMs) encounter challenges in processing long sequences on edge devices due to the quadratic complexity of attention mechanisms and growing memory demands from Key-Value (KV) cache.
GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding
Pixel grounding, encompassing tasks such as Referring Expression Segmentation (RES), has garnered considerable attention due to its immense potential for bridging the gap between vision and language modalities.
SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?
Large Language Models (LLMs) have become integral to daily life, especially advancing as intelligent assistants through on-device deployment on smartphones.
GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices
Recent advancements in Multimodal Large Language Models (MLLMs) have enabled their deployment on mobile devices.
Predictive Data Selection: The Data That Predicts Is the Data That Teaches
Through comprehensive experiments with 1B and 3B parameter models, we demonstrate that models trained on 30B tokens selected with PreSelect surpasses the performance of a vanilla baseline trained on 300B tokens, achieving a 10x reduction in compute requirements.
Autonomous Deep Agent
Through this sophisticated architecture, Deep Agent establishes a novel paradigm in self-governing AI systems, demonstrating robust capability to independently handle intricate, multi-step tasks while maintaining consistent efficiency and reliability through continuous self-optimization.
Data Quality Enhancement on the Basis of Diversity with Large Language Models for Text Classification: Uncovered, Difficult, and Noisy
Subsequently, this model is used to predict the outcomes for the unsampled data, categorizing incorrectly predicted data into uncovered, difficult, and noisy data.
BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices
To be specific, we redesign the dynamic resolution scheme adopted by mainstream MLLMs and implement system optimization for hardware-aware deployment to optimize model inference on mobile phones.
A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models
Preliminary experiments demonstrate that PTFS achieves better pre-training performance, while CPT has lower training cost.
ControlAR: Controllable Image Generation with Autoregressive Models
Firstly, we explore control encoding for AR models and propose a lightweight control encoder to transform spatial inputs (e. g., canny edges or depth maps) into control tokens.
Efficient Test-Time Prompt Tuning for Vision-Language Models
Specifically, we propose Contrastive Prompt Learning (CPT) as the key task for self-supervision.
EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
Surprisingly, we observe that: (1) multimodal prompts and (2) vision-language models with early fusion (e. g., BEIT-3) are beneficial for prompting SAM for accurate referring segmentation.
Ranked #3 on
Referring Expression Segmentation
on RefCOCO+ test B
(using extra training data)
FAGhead: Fully Animate Gaussian Head from Monocular Videos
High-fidelity reconstruction of 3D human avatars has a wild application in visual reality.
Meta-Auxiliary Learning for Micro-Expression Recognition
Micro-expressions (MEs) are involuntary movements revealing people's hidden feelings, which has attracted numerous interests for its objectivity in emotion detection.
DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction
Document image dewarping is a crucial task in computer vision with numerous practical applications.
GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning
To tackle these issues, we propose GPT4Motion, a training-free framework that leverages the planning capability of large language models such as GPT, the physical simulation strength of Blender, and the excellent image generation ability of text-to-image diffusion models to enhance the quality of video synthesis.
ImageBind-LLM: Multi-modality Instruction Tuning
During training, we adopt a learnable bind network to align the embedding space between LLaMA and ImageBind's image encoder.
DPL: Decoupled Prompt Learning for Vision-Language Models
Prompt learning has emerged as an efficient and effective approach for transferring foundational Vision-Language Models (e. g., CLIP) to downstream tasks.
Progressive Visual Prompt Learning with Contrastive Feature Re-formation
To the best of our knowledge, we are the first to demonstrate the superior performance of visual prompts in V-L models to previous prompt-based methods in downstream tasks.
Real-Time Image Demoireing on Mobile Devices
In this paper, we launch the first study on accelerating demoireing networks and propose a dynamic demoireing acceleration method (DDA) towards a real-time deployment on mobile devices.
Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images
Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based solution for weakly-supervised instance segmentation.
Ranked #5 on
Box-supervised Instance Segmentation
on COCO test-dev
(using extra training data)
Hierarchical Reinforcement Learning for Multi-agent MOBA Game
Real Time Strategy (RTS) games require macro strategies as well as micro strategies to obtain satisfactory performance since it has large state space, action space, and hidden information.
