Search Results for author:
Found 62 papers, 36 papers with code
C^3KG: A Chinese Commonsense Conversation Knowledge Graph
Existing commonsense knowledge bases often organize tuples in an isolated manner, which is deficient for commonsense conversational models to plan the next steps.
Global entity alignment with Gated Latent Space Neighborhood Aggregation
In the paper we propose a global entity alignment model with gated latent space neighborhood aggregation (LatsEA) to address this challenge.
Fake it till You Make it: Reward Modeling as Discriminative Prediction
An effective reward model plays a pivotal role in reinforcement learning for post-training enhancement of visual generative models.
AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists
Using our pipeline, we construct AutoSDT-5K, a dataset of 5, 404 coding tasks for data-driven discovery that covers four scientific disciplines and 756 unique Python packages.
Play to Generalize: Learning to Reason Through Game Play
Developing generalizable reasoning capabilities in multimodal large language models (MLLMs) remains challenging.
Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability
Human decision-making in cognitive tasks and daily life exhibits considerable variability, shaped by factors such as task difficulty, individual preferences, and personal experiences.
A Report on the llms evaluating the high school questions
Through an in-depth analysis of the evaluation results, this report reveals the strengths and weaknesses of LLMs in handling high school science questions and discusses their implications for educational practice.
FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation
Subject-driven image generation aims to synthesize novel scenes that faithfully preserve subject identity from reference images while adhering to textual guidance, yet existing methods struggle with a critical trade-off between fidelity and efficiency.
Perception Encoder: The best visual embeddings are not at the output of the network
Together with the core contrastive checkpoint, our PE family of models achieves state-of-the-art performance on a wide variety of tasks, including zero-shot image and video classification and retrieval; document, image, and video Q&A; and spatial tasks such as detection, depth estimation, and tracking.
Ranked #1 on
Object Detection
on COCO minival
(using extra training data)
SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation
To exclude the influence of algorithmic design, we base our experiments on two minimalist architectures: SMPLer-X, which consists of an intermediate step for hand and face localization, and SMPLest-X, an even simpler version that reduces the network to its bare essentials and highlights significant advances in the capture of articulated hands.
VideoDPO: Omni-Preference Alignment for Video Diffusion Generation
Unlike previous image alignment methods that focus solely on either (i) visual quality or (ii) semantic alignment between text and videos, we comprehensively consider both dimensions and construct a preference score accordingly, which we term the OmniScore.
GenEx: Generating an Explorable World
In this work, we take a step toward this goal by introducing GenEx, a system capable of planning complex embodied world exploration, guided by its generative imagination that forms priors (expectations) about the surrounding environments.
ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
To this end, we present ScienceAgentBench, a new benchmark for evaluating language agents for data-driven scientific discovery.
CoCoG-2: Controllable generation of visual stimuli for understanding human concept representation
Similarity judgment tasks are effective for exploring these concepts.
TrAME: Trajectory-Anchored Multi-View Editing for Text-Guided 3D Gaussian Splatting Manipulation
To validate the effectiveness of our method, we analyze 2D examples to demonstrate the improved consistency with the VCAC module.
ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning
This paper presents a new self-supervised video representation learning framework, ARVideo, which autoregressively predicts the next video token in a tailored sequence order.
CoCoG: Controllable Visual Stimuli Generation based on Human Concept Representations
Generating visual stimuli with controlling concepts is the key.
AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation
Expressive human pose and shape estimation (a. k. a.
Ranked #1 on
3D Multi-Person Mesh Recovery
on AGORA
WHAC: World-grounded Humans and Cameras
In this study, we aim to recover expressive parametric human models (i. e., SMPL-X) and corresponding camera poses jointly, by leveraging the synergy between three critical players: the world, the human, and the camera.
Towards Generalizable Tumor Synthesis
Tumor synthesis enables the creation of artificial tumors in medical images, facilitating the training of AI models for tumor detection and segmentation.
Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence
Emotional Intelligence (EI), consisting of emotion perception, emotion cognition and emotion expression, plays the critical roles in improving user interaction experience for the current large language model (LLM) based conversational general AI assistants.
Integration of cognitive tasks into artificial general intelligence test for large models
During the evolution of large models, performance evaluation is necessarily performed to assess their capabilities and ensure safety before practical application.
Advancing EEG/MEG Source Imaging with Geometric-Informed Basis Functions
Here, we present a novel method which utilizes the Brain Geometric-informed Basis Functions (GBFs) as priors to enhance EEG/MEG source imaging.
Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning
This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs).
Digital Life Project: Autonomous 3D Characters with Social Intelligence
In this work, we present Digital Life Project, a framework utilizing language as the universal medium to build autonomous 3D characters, who are capable of engaging in social interactions and expressing with articulated body motions, thereby simulating life in a digital environment.
Ranked #3 on
Motion Synthesis
on InterHuman
Instruct2Attack: Language-Guided Semantic Adversarial Attacks
We propose Instruct2Attack (I2A), a language-guided semantic attack that generates semantically meaningful perturbations according to free-form language instructions.
De-Diffusion Makes Text a Strong Cross-Modal Interface
We demonstrate text as a strong cross-modal interface.
SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation
1) For the data scaling, we perform a systematic investigation on 32 EHPS datasets, including a wide range of scenarios that a model trained on any single dataset cannot handle.
Ranked #2 on
3D Human Pose Estimation
on UBody
Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics
Multi-modal large language models (MLLMs) are trained based on large language models (LLM), with an enhanced capability to comprehend multi-modal inputs and generate textual responses.
PointHPS: Cascaded 3D Human Pose and Shape Estimation from Point Clouds
To tackle these challenges, we propose a principled framework, PointHPS, for accurate 3D HPS from point clouds captured in real-world settings, which iteratively refines point features through a cascaded architecture.
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance.
Ranked #1 on
Image Classification
on iNaturalist 2019
(using extra training data)
Diffusion Models as Masked Autoencoders
There has been a longstanding belief that generation can facilitate a true understanding of visual data.
SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling
Synthetic data has emerged as a promising source for 3D human research as it offers low-cost access to large-scale human datasets.
Learning towards Selective Data Augmentation for Dialogue Generation
As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples.
Unleashing the Power of Visual Prompting At the Pixel Level
This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks.
SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training
Coupling all these designs allows our method to enjoy both competitive performances on text-to-video retrieval and video question answering tasks, and much less pre-training costs by 1. 9X or more.
Masked Autoencoders Enable Efficient Knowledge Distillers
For example, by distilling the knowledge from an MAE pre-trained ViT-L into a ViT-B, our method achieves 84. 0% ImageNet top-1 accuracy, outperforming the baseline of directly distilling a fine-tuned ViT-L by 1. 2%.
High-Resolution Swin Transformer for Automatic Medical Image Segmentation
Most of the existing Transformer-based networks for medical image segmentation are U-Net-like architecture that contains an encoder that utilizes a sequence of Transformer blocks to convert the input medical image from high-resolution representation into low-resolution feature maps and a decoder that gradually recovers the high-resolution representation from low-resolution feature maps.
In Defense of Image Pre-Training for Spatiotemporal Recognition
Inspired by this observation, we hypothesize that the key to effectively leveraging image pre-training lies in the decomposition of learning spatial and temporal features, and revisiting image pre-training as the appearance prior to initializing 3D kernels.
C3KG: A Chinese Commonsense Conversation Knowledge Graph
Existing commonsense knowledge bases often organize tuples in an isolated manner, which is deficient for commonsense conversational models to plan the next steps.
CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation
Recent advances in self-supervised contrastive learning yield good image-level representation, which favors classification tasks but usually neglects pixel-level detailed information, leading to unsatisfactory transfer performance to dense prediction tasks such as semantic segmentation.
Masked Feature Prediction for Self-Supervised Visual Pre-Training
We present Masked Feature Prediction (MaskFeat) for self-supervised pre-training of video models.
Ranked #8 on
Action Recognition
on AVA v2.2
(using extra training data)
Embedding Decomposition for Artifacts Removal in EEG Signals
DeepSeparator employs an encoder to extract and amplify the features in the raw EEG, a module called decomposer to extract the trend, detect and suppress artifact and a decoder to reconstruct the denoised signal.
Phase function estimation from a diffuse optical image via deep learning
The phase function is a key element of a light propagation model for Monte Carlo (MC) simulation, which is usually fitted with an analytic function with associated parameters.
iBOT: Image BERT Pre-Training with Online Tokenizer
We present a self-supervised framework iBOT that can perform masked prediction with an online tokenizer.
Ranked #4 on
Unsupervised Image Classification
on ImageNet
Playing for 3D Human Recovery
Specifically, we contribute GTA-Human, a large-scale 3D human dataset generated with the GTA-V game engine, featuring a highly diverse set of subjects, actions, and scenarios.
Image BERT Pre-training with Online Tokenizer
The success of language Transformers is primarily attributed to the pretext task of masked language modeling (MLM), where texts are first tokenized into semantically meaningful pieces.
Towards an Online Empathetic Chatbot with Emotion Causes
Existing emotion-aware conversational models usually focus on controlling the response contents to align with a specific emotion class, whereas empathy is the ability to understand and concern the feelings and experience of others.
CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning
Semi-supervised learning on class-imbalanced data, although a realistic problem, has been under studied.
Edge Sparse Basis Network: A Deep Learning Framework for EEG Source Localization
EEG source localization is an important technical issue in EEG analysis.
Writing Polishment with Simile: Task, Dataset and A Neural Approach
In this paper, we propose a new task of Writing Polishment with Simile (WPS) to investigate whether machines are able to polish texts with similes as we human do.
Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension
Hence, in this paper, we propose to improve the response generation performance by examining the model's ability to answer a reading comprehension question, where the question is focused on the omitted information in the dialog.
Design and verification of the HXI collimator onboard the ASO-S mission
The HXI collimator (HXI-C) is a spatial modulation X-ray telescope designed to observe hard X-rays emitted by energetic electrons in solar flares.
Instrumentation and Methods for Astrophysics Solar and Stellar Astrophysics High Energy Physics - Experiment
Self-supervised Representation Learning for Evolutionary Neural Architecture Search
To enhance the predictive performance of neural predictors, we devise two self-supervised learning methods from different perspectives to pre-train the architecture embedding part of neural predictors to generate a meaningful representation of neural architectures.
CO2: Consistent Contrast for Unsupervised Visual Representation Learning
Regarding the similarity of the query crop to each crop from other images as "unlabeled", the consistency term takes the corresponding similarity of a positive crop as a pseudo label, and encourages consistency between these two similarities.
Focus-Constrained Attention Mechanism for CVAE-based Response Generation
To model diverse responses for a given post, one promising way is to introduce a latent variable into Seq2Seq models.
EEGdenoiseNet: A benchmark dataset for end-to-end deep learning solutions of EEG denoising
Here, we present EEGdenoiseNet, a benchmark EEG dataset that is suited for training and testing deep learning-based denoising models, as well as for performance comparisons across models.
NPENAS: Neural Predictor Guided Evolution for Neural Architecture Search
In this paper, we propose a neural predictor guided evolutionary algorithm to enhance the exploration ability of EA for NAS (NPENAS) and design two kinds of neural predictors.
Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning
We consider spatial contexts, for which we solve so-called jigsaw puzzles, i. e., each image is cut into grids and then disordered, and the goal is to recover the correct configuration.
Generalized Coarse-to-Fine Visual Recognition with Progressive Training
Computer vision is difficult, partly because the desired mathematical function connecting input and output data is often complex, fuzzy and thus hard to learn.
Deep Retinex Decomposition for Low-Light Enhancement
Based on the decomposition, subsequent lightness enhancement is conducted on illumination by an enhancement network called Enhance-Net, and for joint denoising there is a denoising operation on reflectance.
