Search Results for author:
Found 36 papers, 23 papers with code
Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning
Our findings highlight the critical role of visual perturbation in multimodal mathematical reasoning: better reasoning begins with better seeing.
Segment Concealed Objects with Incomplete Supervision
To mitigate the effect of low-quality segmentation masks, we introduce a series of strategies for pseudo-label generation, storage, and supervision.
ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration
Recent methods have explored reducing the hidden dimensions of the KV cache, but many introduce additional computation through projection layers or suffer from significant performance degradation under high compression ratios.
Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO
Overall, MM-UPT offers a new paradigm for continual, autonomous enhancement of MLLMs in the absence of external supervision.
Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
Recent advancements in large language models (LLMs) have demonstrated impressive chain-of-thought reasoning capabilities, with reinforcement learning (RL) playing a crucial role in this progress.
DVD-Quant: Data-free Video Diffusion Transformers Quantization
Diffusion Transformers (DiTs) have emerged as the state-of-the-art architecture for video generation, yet their computational and memory demands hinder practical deployment.
Low-bit Model Quantization for Deep Neural Networks: A Survey
Therefore, it has become increasingly popular and critical to investigate how to perform the conversion and how to compensate for the information loss.
Enhanced Continual Learning of Vision-Language Models with Model Fusion
Vision-Language Models (VLMs) represent a breakthrough in artificial intelligence by integrating visual and textual modalities to achieve impressive zero-shot capabilities.
QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation
Recently, Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation, surpassing U-Net-based models in terms of performance.
Improving SAM for Camouflaged Object Detection via Dual Stream Adapters
Segment anything model (SAM) has shown impressive general-purpose segmentation performance on natural images, but its performance on camouflaged object detection (COD) is unsatisfactory.
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution
Experimentally, we observe that the degradation of quantization is mainly attributed to the quantization of activation instead of model weights.
BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
One is to compress the DM into 1-bit, aka binarization, alleviating the storage and computation pressure.
RUN: Reversible Unfolding Network for Concealed Object Segmentation
To address this, we propose the Reversible Unfolding Network (RUN), which applies reversible strategies across both mask and RGB domains through a theoretically grounded framework, enabling accurate segmentation.
Pre-trained Molecular Language Models with Random Functional Group Masking
Recent advancements in computational chemistry have leveraged the power of trans-former-based language models, such as MoLFormer, pre-trained using a vast amount of simplified molecular-input line-entry system (SMILES) sequences, to understand and predict molecular properties and activities, a critical step in fields like drug discovery and materials science.
ARB-LLM: Alternating Refined Binarizations for Large Language Models
However, current binarization methods struggle to narrow the distribution gap between binarized and full-precision weights, while also overlooking the column deviation in LLM weight distribution.
Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment
Image quality assessment (IQA) serves as the golden standard for all models' performance in nearly all computer vision fields.
Triple Point Masking
Existing 3D mask learning methods encounter performance bottlenecks under limited data, and our objective is to overcome this limitation.
Pre-trained Graphformer-based Ranking at Web-scale Search (Extended Abstract)
Both Transformer and Graph Neural Networks (GNNs) have been employed in the domain of learning to rank (LTR).
Generative Pre-trained Ranking Model with Over-parameterization at Web-Scale (Extended Abstract)
Learning to rank (LTR) is widely employed in web searches to prioritize pertinent webpages from retrieved content based on input queries.
2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment, which allows advanced SR models to enjoy compact low-bit parameters and efficient integer/bitwise constructions for storage compression and inference acceleration, respectively.
Binarized Diffusion Model for Image Super-Resolution
Nonetheless, due to the model structure and the multi-step iterative attribute of DMs, existing binarization methods result in significant performance degradation.
CondTSF: One-line Plugin of Dataset Condensation for Time Series Forecasting
To mitigate this gap, we theoretically analyze the optimization objective of dataset condensation for TS-forecasting and propose a new one-line plugin of dataset condensation designated as Dataset Condensation for Time Series Forecasting (CondTSF) based on our analysis.
LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design
Recent literature has found that an effective method to customize or further improve large language models (LLMs) is to add dynamic adapters, such as low-rank adapters (LoRA) with Mixture-of-Experts (MoE) structures.
BinaryHPE: 3D Human Pose and Shape Estimation via Binarization
In this work, we propose BinaryHPE, a novel binarization method designed to estimate the 3D human body, face, and hands parameters efficiently.
Image Super-Resolution with Text Prompt Diffusion
Specifically, we first design a text-image generation pipeline to integrate text into the SR dataset through the text degradation representation and degradation model.
Natural Language based Context Modeling and Reasoning for Ubiquitous Computing with Large Language Models: A Tutorial
Recently, with the rise of LLMs and their improved natural language understanding and reasoning capabilities, it has become feasible to model contexts using natural language and perform context reasoning by interacting with LLMs such as ChatGPT and GPT-4.
Toward Reproducing Network Research Results Using Large Language Models
Reproducing research results in the networking community is important for both academia and industry.
SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget
Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) with conditionally-activated parallel experts.
Dual Aggregation Transformer for Image Super-Resolution
Based on the above idea, we propose a novel Transformer model, Dual Aggregation Transformer (DAT), for image SR. Our DAT aggregates features across spatial and channel dimensions, in the inter-block and intra-block dual manner.
Ranked #11 on
Image Super-Resolution
on Manga109 - 4x upscaling
Hierarchical Integration Diffusion Model for Realistic Image Deblurring
Specifically, we perform the DM in a highly compacted latent space to generate the prior feature for the deblurring process.
Recursive Generalization Transformer for Image Super-Resolution
In this work, we propose the Recursive Generalization Transformer (RGT) for image SR, which can capture global spatial information and is suitable for high-resolution images.
Ranked #10 on
Image Super-Resolution
on Manga109 - 4x upscaling
Xformer: Hybrid X-Shaped Transformer for Image Denoising
The channel-wise Transformer block performs direct global context interactions across tokens defined by channel dimension.
Cross Aggregation Transformer for Image Restoration
The core of our CAT is the Rectangle-Window Self-Attention (Rwin-SA), which utilizes horizontal and vertical rectangle window attention in different heads parallelly to expand the attention area and aggregate the features cross different windows.
Accurate Image Restoration with Attention Retractable Transformer
This is considered as a dense attention strategy since the interactions of tokens are restrained in dense regions.
TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
Secondly, we propose TGAN that integrates deep convolutional generative adversarial networks and tensor super-resolution in a cascading manner, to generate high-quality images from random distributions.
