Search Results for author:
Found 59 papers, 27 papers with code
How Does the Experimental Setting Affect the Conclusions of Neural Encoding Models?
Based on these results, we suggest a block-wise cross-validation training method and an adequate data size for increasing the performance of linear encoding models.
CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion
Cross-domain few-shot object detection (CD-FSOD) aims to detect novel objects across different domains with limited class instances.
Ranked #2 on
Cross-Domain Few-Shot Object Detection
on Clipark1k
Cross-Domain Few-Shot
Cross-Domain Few-Shot Object Detection
+2
Metamon-GS: Enhancing Representability with Variance-Guided Densification and Light Encoding
The introduction of 3D Gaussian Splatting (3DGS) has advanced novel view synthesis by utilizing Gaussians to represent scenes.
ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario
However, evaluating the function calling abilities of LLMs in real-world scenarios remains under-explored due to the complexity of data collection and evaluation.
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
We present a general strategy to aligning visual generation models -- both image and video generation -- with human preference.
RobotDiffuse: Motion Planning for Redundant Manipulator based on Diffusion Model
This paper introduces RobotDiffuse, a diffusion model-based approach for motion planning in redundant manipulators.
SCENIC: Scene-aware Semantic Navigation with Instruction-guided Control
To address these limitations, we introduce SCENIC, a diffusion model designed to generate human motion that adapts to dynamic terrains within virtual scenes while enabling semantic control through natural language.
Toy-GS: Assembling Local Gaussians for Precisely Rendering Large-Scale Free Camera Trajectories
Currently, 3D rendering for large-scale free camera trajectories, namely, arbitrary input camera trajectories, poses significant challenges: 1) The distribution and observation angles of the cameras are irregular, and various types of scenes are included in the free trajectories; 2) Processing the entire point cloud and all images at once for large-scale scenes requires a substantial amount of GPU memory.
Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding
Existing safe generation methods typically focus on suppressing inappropriate content by erasing undesired concepts from visual representations, while neglecting to sanitize the textual representation.
CogVLM2: Visual Language Models for Image and Video Understanding
Beginning with VisualGLM and CogVLM, we are continuously exploring VLMs in pursuit of enhanced vision-language fusion, efficient higher-resolution architecture, and broader modalities and applications.
Ranked #10 on
Visual Question Answering
on MM-Vet
CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
We present CogVideoX, a large-scale text-to-video generation model based on diffusion transformer, which can generate 10-second continuous videos aligned with text prompt, with a frame rate of 16 fps and resolution of 768 * 1360 pixels.
Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance
In this paper, we present a novel Geometric Preserving Ground-to-Aerial (G2A) image synthesis (GPG2A) model that can generate realistic aerial images from ground images.
DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning
Vision-language models (VLMs) have been applied to robot task planning problems, where the robot receives a task in natural language and generates plans based on visual inputs.
SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation
We introduce SpreadsheetBench, a challenging spreadsheet manipulation benchmark exclusively derived from real-world scenarios, designed to immerse current large language models (LLMs) in the actual workflow of spreadsheet users.
AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models
Evaluating the alignment capabilities of large Vision-Language Models (VLMs) is essential for determining their effectiveness as helpful assistants.
LVBench: An Extreme Long Video Understanding Benchmark
To address this gap, we introduce LVBench, a benchmark specifically designed for long video understanding.
Rethinking Early-Fusion Strategies for Improved Multispectral Object Detection
In this paper, we address this issue by improving the performance of efficient single-branch structures.
Aerial-NeRF: Adaptive Spatial Partitioning and Sampling for Large-Scale Aerial Rendering
To that end, we propose Aerial-NeRF with three innovative modifications for jointly adapting NeRF in large-scale aerial rendering: (1) Designing an adaptive spatial partitioning and selection method based on drones' poses to adapt different flight trajectories; (2) Using similarity of poses instead of (expert) network for rendering speedup to determine which region a new viewpoint belongs to; (3) Developing an adaptive sampling approach for rendering performance improvement to cover the entire buildings at different heights.
NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Prompts
To fill this gap, we propose NaturalCodeBench (NCB), a challenging code benchmark designed to mirror the complexity and variety of scenarios in real coding tasks.
AG-NeRF: Attention-guided Neural Radiance Fields for Multi-height Large-scale Outdoor Scene Rendering
Existing neural radiance fields (NeRF)-based novel view synthesis methods for large-scale outdoor scenes are mainly built on a single altitude.
A Cause-Effect Look at Alleviating Hallucination of Knowledge-grounded Dialogue Generation
Recently, knowledge-grounded dialogue generation models, that intentionally invoke external knowledge resources to more informative responses, are also proven to be effective in reducing hallucination.
AutoWebGLM: A Large Language Model-based Web Navigating Agent
Large language models (LLMs) have fueled many intelligent web agents, but most existing ones perform far from satisfying in real-world web navigation tasks due to three factors: (1) the complexity of HTML text data (2) versatility of actions on webpages, and (3) task difficulty due to the open-domain nature of the web.
ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline
Large language models (LLMs) have shown excellent mastering of human language, but still struggle in real-world applications that require mathematical problem-solving.
ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback
The work presents our practices of aligning LLMs with human preferences, offering insights into the challenges and solutions in RLHF implementations.
MapGuide: A Simple yet Effective Method to Reconstruct Continuous Language from Brain Activities
In contrast, we propose a simple yet effective method that guides text reconstruction by directly comparing them with the predicted text embeddings mapped from brain activities.
PointCore: Efficient Unsupervised Point Cloud Anomaly Detector Using Local-Global Features
Three-dimensional point cloud anomaly detection that aims to detect anomaly data points from a training set serves as the foundation for a variety of applications, including industrial inspection and autonomous driving.
MulCogBench: A Multi-modal Cognitive Benchmark Dataset for Evaluating Chinese and English Computational Language Models
Results show that language models share significant similarities with human cognitive data and the similarity patterns are modulated by the data modality and stimuli complexity.
OpenEQA: Embodied Question Answering in the Era of Foundation Models
We present a modern formulation of Embodied Question Answering (EQA) as the task of understanding an environment well enough to answer questions about it in natural language.
Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition
To establish an optimal multimodal semantic environment for text modality, we develop a modality-aware prompting module (MAP), which effectively aligns and fuses features from text, video and audio modalities with similarity-based modality alignment and cross-modality attention mechanism.
Ranked #2 on
Multimodal Intent Recognition
on MIntRec
AlignBench: Benchmarking Chinese Alignment of Large Language Models
Alignment has become a critical step for instruction-tuned Large Language Models (LLMs) to become helpful assistants.
CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models
In this paper, we present CharacterGLM, a series of models built upon ChatGLM, with model sizes ranging from 6B to 66B parameters.
Robust Tumor Segmentation with Hyperspectral Imaging and Graph Neural Networks
Despite the limited dataset, the GNN-based model significantly outperforms context-agnostic approaches, accurately distinguishing between healthy and tumor tissues, even in images from previously unseen patients.
Tuning In to Neural Encoding: Linking Human Brain and Artificial Supervised Representations of Language
To understand the algorithm that supports the human brain's language representation, previous research has attempted to predict neural responses to linguistic stimuli using embeddings generated by artificial neural networks (ANNs), a process known as neural encoding.
GeoDTR+: Toward generic cross-view geolocalization via geometric disentanglement
We attribute this deficiency to the lack of ability to extract the geometric layout of visual features and models' overfitting to low-level details.
Human Emotion Recognition Based On Galvanic Skin Response signal Feature Selection and SVM
A novel human emotion recognition method based on automatically selected Galvanic Skin Response (GSR) signal features and SVM is proposed in this paper.
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations.
Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worlds
Each situation corresponds to a state instance wherein a robot is potentially unable to complete a task using a solution that normally works.
TFDet: Target-Aware Fusion for RGB-T Pedestrian Detection
Different from them, we comprehensively analyze the impacts of false positives on the detection performance and find that enhancing feature contrast can significantly reduce these false positives.
LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
LLM+P takes in a natural language description of a planning problem, then returns a correct (or optimal) plan for solving that problem in natural language.
Spatial-Language Attention Policies for Efficient Robot Learning
We see a 4x improvement over baseline in mobile manipulation setting.
GLM-Dialog: Noise-tolerant Pre-training for Knowledge-grounded Dialogue Generation
We present GLM-Dialog, a large-scale language model (LLM) with 10B parameters capable of knowledge-grounded conversation in Chinese using a search engine to access the Internet knowledge.
Intra-operative Brain Tumor Detection with Deep Learning-Optimized Hyperspectral Imaging
Surgery for gliomas (intrinsic brain tumors), especially when low-grade, is challenging due to the infiltrative nature of the lesion.
Time-sensitive Learning for Heterogeneous Federated Edge Intelligence
A joint optimization algorithm is proposed to minimize the overall time consumption of model training by selecting participating edge servers, local epoch number.
Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondence
We attribute this deficiency to the lack of ability to extract the spatial configuration of visual feature layouts and models' overfitting on low-level details from the training set.
Cross-View Image Sequence Geo-localization
In this paper, we present the first cross-view geo-localization method that works on a sequence of limited FOV images.
Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization
This problem is challenging, as it requires planning wiping actions while reasoning over uncertain latent dynamics of crumbs and spills captured via high-dimensional visual observations.
Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization
While (Lu and Sa, 2021) have recently provided an optimal rate for non-convex stochastic decentralized optimization with weight matrices defined over linear graphs, the optimal rate with general weight matrices remains unclear.
Robot Task Planning and Situation Handling in Open Worlds
For systematic evaluations, we collected a dataset that includes 561 execution-time situations in a dining domain, where each situation corresponds to a state instance of a robot being potentially unable to complete a task using a solution that normally works.
COUCH: Towards Controllable Human-Chair Interactions
In this work, we study the problem of synthesizing scene interactions conditioned on different contact positions on the object.
Deep Class Incremental Learning from Decentralized Data
In this paper, we focus on a new and challenging decentralized machine learning paradigm in which there are continuous inflows of data to be addressed and the data are stored in multiple repositories.
Visual and Object Geo-localization: A Comprehensive Survey
The concept of geo-localization refers to the process of determining where on earth some `entity' is located, typically using Global Positioning System (GPS) coordinates.
Actor-Critic Algorithm for High-dimensional PDEs
Our model advances the state-of-the-art machine learning PDE solvers in a few aspects: 1) the trainable parameters are reduced by $N$ times, where $N$ is the number of steps to discretize the PDE in time, 2) the model convergence rate is an order of magnitude faster, 3) our model has fewer tuning hyperparameters.
BIG-bench Machine Learning
Vocal Bursts Intensity Prediction
Object Tracking and Geo-localization from Street Images
Geo-localizing static objects from street images is challenging but also very important for road asset mapping and autonomous driving.
Episodic memory governs choices: An RNN-based reinforcement learning model for decision-making task
Typical methods to study cognitive function are to record the electrical activities of animal neurons during the training of animals performing behavioral tasks.
Efficient Golf Ball Detection and Tracking Based on Convolutional Neural Networks and Kalman Filter
The detection is performed on small image patches instead of the entire image to increase the performance of small ball detection.
Actor-Critic Algorithm for High-dimensional Partial Differential Equations
We develop a deep learning model to effectively solve high-dimensional nonlinear parabolic partial differential equations (PDE).
Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization
Experiment results show that SCT improves accuracy of single Resnet-50 on ImageNet by 1. 7% and 11. 5% accuracy when testing on image sizes of 224 and 128 respectively.
