Search Results for author:
Found 21 papers, 10 papers with code
R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning
Despite recent breakthroughs in reasoning-enhanced large language models (LLMs) like DeepSeek-R1, incorporating inference-time reasoning into machine translation (MT), where human translators naturally employ structured, multi-layered reasoning chain-of-thoughts (CoTs), is yet underexplored.
BFA: Best-Feature-Aware Fusion for Multi-View Fine-grained Manipulation
Built upon the visual backbone of the policy network, we design a lightweight network to predict the importance score of each view.
RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World
Existing policy learning methods predominantly adopt the task-centric paradigm, necessitating the collection of task data in an end-to-end manner.
What Do You Want? User-centric Prompt Generation for Text-to-image Synthesis via Multi-turn Guidance
To achieve this, we mined 15 essential dimensions for high-quality prompts from advanced users and curated a multi-turn dataset.
MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment
This paper introduces MM-Instruct, a large-scale dataset of diverse and high-quality visual instruction data designed to enhance the instruction-following capabilities of large multimodal models (LMMs).
Ranked #137 on
Visual Question Answering
on MM-Vet
BreakGPT: A Large Language Model with Multi-stage Structure for Financial Breakout Detection
To address these issues, we introduce BreakGPT, the first large language model for financial breakout detection.
PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detection
Pillar-based methods mainly employ randomly initialized 2D convolution neural network (ConvNet) for feature extraction and fail to enjoy the benefits from the backbone scaling and pretraining in the image domain.
GMM: Delving into Gradient Aware and Model Perceive Depth Mining for Monocular 3D Detection
In light of the success of sample mining techniques in 2D object detection, we propose a simple yet effective mining strategy for improving depth perception in 3D object detection.
Vision Learners Meet Web Image-Text Pairs
In this work, given the excellent scalability of web data, we consider self-supervised pre-training on noisy web sourced image-text paired data.
A Simple Framework for Text-Supervised Semantic Segmentation
LoDA and SimSeg jointly ameliorate a vanilla CLIP to produce impressive semantic segmentation results.
Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective
This work simultaneously considers the discriminability and transferability properties of deep representations in the typical supervised learning task, i. e., image classification.
Contrastive Vision-Language Pre-training with Limited Resources
However, these works require a tremendous amount of data and computational resources (e. g., billion-level web data and hundreds of GPUs), which prevent researchers with limited resources from reproduction and further exploration.
PP-YOLOv2: A Practical Object Detector
To meet these two concerns, we comprehensively evaluate a collection of existing refinements to improve the performance of PP-YOLO while almost keep the infer time unchanged.
OTA: Optimal Transport Assignment for Object Detection
Recent advances in label assignment in object detection mainly seek to independently define positive/negative training samples for each ground-truth (gt) object.
Ranked #74 on
Object Detection
on COCO test-dev
A Reinforcement learning method for Optical Thin-Film Design
Machine learning, especially deep learning, is dramatically changing the methods associated with optical thin-film inverse design.
LLA: Loss-aware Label Assignment for Dense Pedestrian Detection
A joint loss is then defined as the weighted summation of cls and reg losses as the assigning indicator.
ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval
Retrieving content relevant images from a large-scale fine-grained dataset could suffer from intolerably slow query speed and highly redundant storage cost, due to high-dimensional real-valued embeddings which aim to distinguish subtle visual differences of fine-grained objects.
Delving into the Imbalance of Positive Proposals in Two-stage Object Detection
The first imbalance lies in the large number of low-quality RPN proposals, which makes the R-CNN module (i. e., post-classification layers) become highly biased towards the negative proposals in the early training stage.
NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing
To acquire the visible parts, a novel Paired-Box Model (PBM) is proposed to simultaneously predict the full and visible boxes of a pedestrian.
PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppression
PS-RCNN first detects slightly/none occluded objects by an R-CNN module (referred as P-RCNN), and then suppress the detected instances by human-shaped masks so that the features of heavily occluded instances can stand out.
Ranked #2 on
Object Detection
on WiderPerson
A new multilayer optical film optimal method based on deep q-learning
This model can converge the global optimum of the optical thin film structure, this will greatly improve the design efficiency of multi-layer films.
