Search Results for author:
Found 30 papers, 14 papers with code
Slow Perception: Let's Perceive Geometric Figures Step-by-step
Recently, "visual o1" began to enter people's vision, with expectations that this slow-thinking design can solve visual reasoning tasks, especially geometric math problems.
Qwen2.5 Technical Report
In addition, for hosted solutions, the proprietary models currently include two mixture-of-experts (MoE) variants: Qwen2. 5-Turbo and Qwen2. 5-Plus, both available from Alibaba Cloud Model Studio.
Ranked #4 on
Mathematical Reasoning
on AIME24
Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusion
Recent diffusion-based Single-image 3D portrait generation methods typically employ 2D diffusion models to provide multi-view knowledge, which is then distilled into 3D representations.
P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs
Recent advancements in large language models (LLMs) showcase varied multilingual capabilities across tasks like translation, code generation, and reasoning.
No Re-Train, More Gain: Upgrading Backbones with Diffusion Model for Few-Shot Segmentation
For the second issue, due to the varying granularity of transformed priors from diverse annotation types, we conceptualize these multi-granular transformed priors as analogous to noisy intermediates at different steps of a diffusion model.
Qwen2 Technical Report
This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models.
Ranked #1 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
Focus Anywhere for Fine-grained Multi-page Document Understanding
Modern LVLMs still struggle to achieve fine-grained document understanding, such as OCR/translation/caption for regions of interest to the user, tasks that require the context of the entire page, or even multiple pages.
On the Adversarial Robustness of Learning-based Image Compression Against Rate-Distortion Attacks
Using the performance variations as indicators, we evaluate the adversarial robustness of eight predominant LIC algorithms against diverse attacks.
OneChart: Purify the Chart Structural Extraction via One Auxiliary Token
To address this, we propose OneChart: a reliable agent specifically devised for the structural extraction of chart information.
MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs
Training LLMs at this scale brings unprecedented challenges to training efficiency and stability.
Small Language Model Meets with Reinforced Vision Vocabulary
In Vary-toy, we introduce an improved vision vocabulary, allowing the model to not only possess all features of Vary but also gather more generality.
Ranked #209 on
Visual Question Answering
on MM-Vet
Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models
Accordingly, we propose Vary, an efficient and effective method to scale up the vision vocabulary of LVLMs.
Ranked #144 on
Visual Question Answering
on MM-Vet
Merlin:Empowering Multimodal LLMs with Foresight Minds
Then, FIT requires MLLMs to first predict trajectories of related objects and then reason about potential future events based on them.
Ranked #160 on
Visual Question Answering
on MM-Vet
DreamLLM: Synergistic Multimodal Comprehension and Creation
This paper presents DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models (MLLMs) empowered with frequently overlooked synergy between multimodal comprehension and creation.
Ranked #5 on
Visual Question Answering
on MMBench
ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning
Based on precise referring instruction, we propose ChatSpot, a unified end-to-end multimodal large language model that supports diverse forms of interactivity including mouse clicks, drag-and-drop, and drawing boxes, which provides a more flexible and seamless interactive experience.
PolyLM: An Open Source Polyglot Large Language Model
Large language models (LLMs) demonstrate remarkable ability to comprehend, reason, and generate following nature language instructions.
Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition
Moreover, we propose to train the Aformer in a multi-pass manner, and investigate three cross-information fusion methods to effectively combine the information from both general and accent encoders.
1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation
In this report, we successfully validated the effectiveness of the decoupling strategy in video panoptic segmentation.
Collaborative Multi-BS Power Management for Dense Radio Access Network using Deep Reinforcement Learning
Network energy efficiency is a main pillar in the design and operation of wireless communication systems.
DWRSeg: Rethinking Efficient Acquisition of Multi-scale Contextual Information for Real-time Semantic Segmentation
In this method, the multi-rate depth-wise dilated convolutions take a simpler role in feature extraction: performing simple semantic-based morphological filtering with one desired receptive field in the second step based on each concise feature map of region form provided by the first step, to improve their efficiency.
Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality?
The lack of competency awareness makes NMT untrustworthy.
Phonetic-assisted Multi-Target Units Modeling for Improving Conformer-Transducer ASR system
Exploiting effective target modeling units is very important and has always been a concern in end-to-end automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Continuous Human Action Detection Based on Wearable Inertial Data
Human action detection is a hot topic, which is widely used in video surveillance, human machine interface, healthcare monitoring, gaming, dancing training and musical instrument teaching.
Non-Parametric Online Learning from Human Feedback for Neural Machine Translation
We study the problem of online learning with human feedback in the human-in-the-loop machine translation, in which the human translators revise the machine-generated translations and then the corrected translations are used to improve the neural machine translation (NMT) system.
ChMusic: A Traditional Chinese Music Dataset for Evaluation of Instrument Recognition
This paper propose a traditional Chinese music dataset for training model and performance evaluation, named ChMusic.
Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning
In this paper, we propose a Non-Homogeneous Haze Removal Network (NHRN) via artificial scene prior and bidimensional graph reasoning.
WB-DETR: Transformer-Based Detector Without Backbone
In this paper, we propose WB-DETR (DETR-based detector Without Backbone) to prove that the reliance on CNN features extraction for a transformer-based detector is not necessary.
Arbitrary-Oriented Object Detection in Remote Sensing Images Based on Polar Coordinates
In this article, we introduce the polar coordinate system to the deep learning detector for the first time, and propose an anchor free Polar Remote Sensing Object Detector (P-RSDet), which can achieve competitive detection accuracy via using simpler object representation model and less regression parameters.
Ranked #14 on
Oriented Object Detection
on DOTA 1.0
Ensemble Chinese End-to-End Spoken Language Understanding for Abnormal Event Detection from audio stream
Previous end-to-end SLU models are primarily used for English environment due to lacking large scale SLU dataset in Chines, and use only one ASR model to extract features from speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
