104 accepted papers
Large Vision-Language Models (LVLMs) have achieved impressive progress across various applications but remain vulnerable to malicious queries. Existing safety alignment approaches typically fail to resist malicious queries while preserving utility on benign ones effectively. To address these challen
Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in training sets, compromising the validity of reported performance. While detection methods have been developed for the pre-tra…
Lifting 2D open-vocabulary understanding into 3D Gaussian Splatting (3DGS) scenes is a critical challenge. Mainstream methods, built on an embedding paradigm, suffer from three key flaws: (i) geometry-semantic inconsistency, where points, rather than objects, serve as the semantic basis, limiting se
While Large Language Models (LLMs) excel at code generation, their inherent tendency toward verbatim memorization of training data introduces critical risks like copyright infringement, insecurity emission, and deprecated API utilization, etc. A straightforward yet promising defense is unlearning, i
We address the challenge of reconstructing long dynamic scenes from multi-view videos in a storage-efficient manner. Recent advances in Gaussian Splatting and its extensions to dynamic scenes have demonstrated impressive visual quality, but remain limited to short duration (<10 s), large storage siz
We propose MoRe-ERL, a framework that combines Episodic Reinforcement Learning (ERL) and residual learning, which refines preplanned reference trajectories into safe, feasible, and efficient task-specific trajectories. This framework is general enough to incorporate into arbitrary ERL methods and mo…
Preference-based reinforcement learning (PbRL) learns policies from human trajectory-level comparisons, avoiding explicit reward design and expert demonstrations. Existing methods typically train utility functions on trajectory or segment-level preferences while relying on per-step utility estimates…
Recent advances in Multi-modal Large Language Models (MLLMs) have showcased remarkable capabilities in vision-language understanding. However, enabling robust video spatial reasoning—the ability to comprehend object locations, orientations, and inter-object relationships in dynamic 3D scenes—remains
We present the B-spline Encoded Action Sequence Tokenizer (BEAST), a novel action tokenizer that encodes action sequences into compact discrete or continuous tokens using B-splines. In contrast to existing action tokenizers based on vector quantization or byte pair encoding, BEAST requires no separ…
Current advanced long-context language models offer great potential for real-world software engineering applications. However, progress in this critical domain remains hampered by a fundamental limitation: the absence of a rigorous evaluation framework for long code understanding. To gap this obstac…
Code generation models have shown significant potential for programming tasks. However, existing training methods like supervised fine-tuning face key limitations: they do not effectively teach models to prioritize correct over incorrect solutions in ambiguous situations, nor do they effectively opt…
Spatial contexts, such as the backgrounds and surroundings, are considered critical in Human-Object Interaction (HOI) recognition, especially when the instance-centric foreground is blurred or occluded. Recent advancements in HOI detectors are usually built upon detection transformer pipelines. Whil…
In this work, we investigate the generation of high-fidelity, audio-driven 3D Gaussian talking heads from monocular videos. We present DGTalker, an innovative framework designed for real-time, high-fidelity, and 3D-aware talking head synthesis. By leveraging Gaussian generative priors and treating t…
Maximum entropy reinforcement learning (MaxEnt-RL) has become the standard approach to RL due to its beneficial exploration properties. Traditionally, policies are parameterized using Gaussian distributions, which significantly limits their representational capacity. Diffusion-based policies offer a…
Long-form video understanding has always been a challenging problem due to the significant redundancy in both temporal and spatial contents. This challenge is further exacerbated by the limited context length of Multimodal Large Language Models (MLLMs). To address this issue, many previous works hav…
Code generation models have shown significant potential for automating programming tasks. However, the challenge of generating accurate and reliable code persists due to the highly complex and long-reasoning nature of the task. Even state-of-the-art models often fail in code generation due to small…
Despite the remarkable successes of general-purpose neural networks, such as MLPs and Transformers, we find that they exhibit notable shortcomings in modeling and reasoning about periodic phenomena, achieving only marginal performance within the training domain and failing to generalize effectively…
This paper introduces IRIS, an Immersive Robot Interaction System leveraging Extended Reality (XR). Existing XR-based systems enable efficient data collection but are often challenging to reproduce and reuse due to their specificity to particular robots, objects, simulators, and environments. IRIS a…
The Transformer architecture has emerged as a landmark advancement within the broad field of artificial intelligence, effectively catalyzing the advent of large language models (LLMs). However, despite its remarkable capabilities and the substantial progress it has facilitated, the Transformer archi…
Detecting tricky bugs in plausible programs, those that pass existing test suites yet still contain bugs, remains a significant challenge in software testing. To address this problem, we propose TrickCatcher, an LLM-powered approach to generating test cases for uncovering bugs in plausible programs.…
Face animation is a challenging task. Existing model-based methods (utilizing 3DMMs or landmarks) often result in a model-like reconstruction effect, which doesn't effectively preserve identity. Conversely, model-free approaches face challenges in attaining a decoupled and semantically rich feature…
Text-Video Retrieval (TVR) aims to align and associate relevant video content with corresponding natural language queries. Most existing TVR methods are based on large-scale pre-trained vision-language models (e.g., CLIP). However, due to CLIP's inherent plain structure, few TVR methods explore the…
For mesh animation sequences with consistent topology, traditional compression methods are well established, but deep learning approaches are emerging. This paper presents a novel deep learning framework for vertex position reconstruction by encoding displacements. We propose LoD-Uniform Partitionin…
Human-object interaction (HOI) detectors with popular query-transformer architecture have achieved promising performance. However, accurately identifying uncommon visual patterns and distinguishing between ambiguous HOIs continue to be difficult for them. We observe that these difficulties may arise…
Utilizing uniformly distributed sparse annotations, weakly supervised learning alleviates the heavy reliance on fine-grained annotations in point cloud semantic segmentation tasks. However, few works discuss the inhomogeneity of sparse annotations, albeit it is common in real-world scenarios. Theref…
Robotic manipulation systems benefit from complementary sensing modalities, where each provides unique environmental information. Point clouds capture detailed geometric structure, while RGB images provide rich semantic context. Current point cloud methods struggle to capture fine-grained detail, es…
Periodicity, as one of the most important basic characteristics, lays the foundation for facilitating structured knowledge acquisition and systematic cognitive processes within human learning paradigms. However, the potential flaws of periodicity modeling in Transformer affect the learning efficienc…
With the advent of neural language models, the performance of code generation has been significantly boosted. However, the problem of repetitions during the generation process continues to linger. Previous work has primarily focused on content repetition, which is merely a fraction of the broader re…
How to design reinforcement learning (RL) tasks that effectively unleash the reasoning capability of large language models (LLMs) remains an open question. Existing RL tasks (e.g., math, programming, and constructing reasoning tasks) suffer from three key limitations: (1) Scalability. They rely heav…
The evolution of point cloud processing algorithms necessitates an accurate assessment for their quality. Previous works consistently regard point cloud quality assessment (PCQA) as a MOS regression problem and devise a deterministic mapping, ignoring the stochasticity in generating MOS from subject
This work introduces Transformer-based Off-Policy Episodic Reinforcement Learning (TOP-ERL), a novel algorithm that enables off-policy updates in the ERL framework. In ERL, policies predict entire action trajectories over multiple time steps instead of single actions at every time step. These trajec…
In robotics, the design of robot behavior trees generally requires roboticists to comprehensively and customizable consider all the relevant factors including the robot hardware capabilities, task descriptions, etc, posing great challenges for design quality and efficiency. The mainstream practice o
The recent progress in Large Language Models (LLM) has spurred various advancements in image-language conversation agents while how to build a proficient video-based dialogue system is still under exploration. Considering the extensive scale of LLM and visual backbone minimal GPU memory is left for…
Machine learning models are increasingly being deployed in real-world contexts. However, systematic studies on their transferability to specific and critical applications are underrepresented in the research literature. An important example is visual anomaly detection (VAD) for robotic power line in…
Large Language Models (LLMs) have shown promise in automated code generation but typically excel only in simpler tasks such as generating standalone code units. However, real-world software development often involves complex code repositories with complex dependencies and extensive documentation. To…
How to evaluate the coding abilities of Large Language Models (LLMs) remains an open question. We find that existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs.To address the knowledge gap, we propose a new benchmark…
Despite alleviating the dependence on dense annotations inherent to fully supervised methods, weakly supervised point cloud semantic segmentation suffers from inadequate supervision signals. In response to this challenge, we introduce a novel perspective that imparts auxiliary constraints by regulat…
The Graph Fourier Transform (GFT) has achieved remarkable success in point cloud attribute compression due to its adaptability in handling irregular signals. However, the conventional graph-based attribute compression method mostly relies on geometry information to construct the Laplace matrix. In t…
Large Language Models (LLMs) have recently made significant advances in code generation through the ‘Chain-of-Thought’ prompting technique. This technique empowers the model to autonomously devise “solution plans” to tackle intricate programming challenges, thereby improving its performance in code…
How to evaluate Large Language Models (LLMs) in code generation remains an open question. Many benchmarks have been proposed, but they have two limitations, i.e., data leakage and lack of domain-specific evaluation. The former hurts the fairness of benchmarks, and the latter hinders practitioners f…
Recent statements about the impressive capabilities of large language models (LLMs) are usually supported by evaluating on open-access benchmarks. Considering the vast size and wide-ranging sources of LLMs’ training data, it could explicitly or implicitly include test data, leading to LLMs being mor…
Addressing the limitation of context length in large language models for code-related tasks is the primary focus of this paper. Existing LLMs are constrained by their pre-trained context lengths, leading to performance issues in handling long complex code sequences. Inspired by how human programmers…
Recently, Large Language Models (LLMs) have shown impressive abilities in code generation. However, existing LLMs' decoding strategies are designed for Natural Language (NL) generation, overlooking the differences between NL and programming languages (PL). Due to this oversight, a better decoding st…
Open vocabulary object detection (OVD) aims at seeking an optimal object detector capable of recognizing objects from both base and novel categories. Recent advances leverage knowledge distillation to transfer insightful knowledge from pre-trained large-scale vision-language models to the task of ob…
Weak supervision has proven to be an effective strategy for reducing the burden of annotating semantic segmentation tasks in 3D space. However, unconstrained or heuristic weakly supervised annotation forms may lead to suboptimal label efficiency. To address this issue, we propose a novel label recom…
This work introduces Mamba Imitation Learning (MaIL), a novel imitation learning (IL) architecture that offers a computationally efficient alternative to state-of-the-art (SoTA) Transformer policies. Transformer-based policies have achieved remarkable results due to their ability in handling human-r…
Current advancements in reinforcement learning (RL) have predominantly focused on learning step-based policies that generate actions for each perceived state. While these methods efficiently leverage step information from environmental interaction, they often ignore the temporal correlation between…
Large language models (LLMs) have showcased remarkable potential across various tasks by conditioning on prompts. However, the quality of different human-written prompts leads to substantial discrepancies in LLMs’ performance, and improving prompts usually necessitates considerable human effort and…
Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. To date, most of the state-of-the-art TVR methods learn image-to-video transfer learning based on the large-scale pre-trained vision-language models (e.g., CLIP). However, fully fine-tuning these pre-train…
With the proliferation of sensor devices, the extensive utilization of three-dimensional data in multimedia continues to grow. Point clouds are widely adopted within this domain because they are one of the most intuitive representations of three-dimensional data. However, the substantial volume of p…
The efficient storage and transportation requirements of point clouds promote the development of point cloud compression algorithms. In this paper, we develop a novel point cloud geometry compression using sequential slice representation. Unlike the limited contexts in conventional codecs and other…
This work introduces Variational Diffusion Distillation (VDD), a novel method that distills denoising diffusion policies into Mixtures of Experts (MoE) through variational inference. Diffusion Models are the current state-of-the-art in generative modeling due to their exceptional ability to accurate…
Point cloud place recognition is key to auto-driving, navigation, localization, and robotics. It targets finding a similar scene of the query in the database via extracted compact point features. The core challenge focuses on obtaining descriptive features to enhance retrieval performance. Existing…
Compressive autoencoders (CAEs) play an important role in deep learning-based image compression, but large-scale CAEs are computationally expensive. We propose a framework with three techniques to enable efficient CAE-based image coding: 1) Spatially-adaptive convolution and normalization operators…
Various gradient compression algorithms have been proposed to alleviate the communication bottleneck in distributed learning, and they have demonstrated effectiveness in terms of high compression ratios and theoretical low communication complexity. However, when it comes to practically training mod…
Visual attention does not always capture the essential object representation desired for robust predictions. Attention modules tend to underline not only the target object but also the common co-occurring context that the module thinks helpful in the training. The problem is rooted in the confoundin…
Learning an accurate entropy model is a fundamental way to remove the redundancy in point cloud compression. Recently, the octree-based auto-regressive entropy model which adopts the self-attention mechanism to explore dependencies in a large-scale context is proved to be promising. However, heavy g…
Recently, self-attention networks achieve impressive performance in point cloud segmentation due to their superiority in modeling long-range dependencies. However, compared to self-attention mechanism, we find graph convolutions show a stronger ability in capturing local geometry information with le…
As a crucial infrastructure of intelligent mobile robots, LiDAR-Inertial odometry (LIO) provides the basic capability of state estimation by tracking LiDAR scans. The high-accuracy tracking generally involves the k\text{NN}k\text{NN} search, which is used with minimizing the point-to-plane distance.…
Point cloud completion aims at estimating the complete data of objects from degraded observations. Despite existing completion methods achieving impressive performances, they rely heavily on degraded-complete data pairs for supervision. In this work, we propose a novel framework named Null-Space Dif…
Movement Primitives (MPs) are a well-known concept to represent and generate modular trajectories. MPs can be broadly categorized into two types: (a) dynamics-based approaches that generate smooth trajectories from any initial state, e. g., Dynamic Movement Primitives (DMPs), and (b) probabilistic a
Image-text pretrained models, e.g., CLIP, have shown impressive general multi-modal knowledge learned from large-scale image-text data pairs, thus attracting increasing attention for their potential to improve visual representation learning in the video domain. In this paper, based on the CLIP model…
Large language models (LLMs) have demonstrated an impressive ability to generate codes on competitive programming tasks. However, with limited sample numbers, LLMs still suffer from poor accuracy. Inspired by the process of human programming, we propose a generate-and-edit approach named Self-Edit t…
In this paper, we prove that it is feasible to perform mesh quality assessment by sampling it into point cloud. We propose a general and efficient surface-sampling based framework that can deal with various types and levels of distortions with less complexity. In this method, the original and distor…
To copy with the extreme variations of illumination and rotation in the real world, popular descriptors have captured more invariance recently, but more invariance makes descriptors less informative. So this paper designs a unique attention guided framework (named AISLFD) to select appropriate invar…
As a common problem in the visual world, contextual bias means the recognition may depend on the co-occurrence context rather than the objects themselves, which is even more severe in multi-label tasks due to multiple targets and the absence of location. Although some studies have focused on tacklin…
Keypoint extraction including both keypoint detection and description is a fundamental step in a wide range of geometric multimedia applications. In recent years, many learning-based approaches for keypoint extraction emerge and achieve promising results. However, they usually design network archite…
Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently. However, fine-tuning an extremely large-scale pre-trained language model on limited target datasets is often plagued by overfitting and representation degradation. In this paper, we…
Point cloud completion is the task of estimating the complete point cloud from the partial observation. Most of the existing methods tend to recover global shapes of 3D objects and usually lack local details. These methods rely merely on distance metrics between point sets as loss functions, which h…
Previous reinforcement learning (RL) based image restoration studies typically train RL agents to search for recovery tools from a constructed toolset and iteratively recover images. However, we argue that these agents rely on pre-trained RL models with fixed-length paths for restoration, which perf…
In this paper, we study the problem of networked multi-agent reinforcement learning (MARL), where a number of agents are deployed as a partially connected network and each interacts only with nearby agents. Networked MARL requires all agents to make decisions in a decentralized manner to optimize a…
3D meshes are widely employed to represent geometry structure of 3D shapes. Due to limitation of scanning sensor precision and other issues, meshes are inevitably affected by noise, which hampers the subsequent applications. Convolultional neural networks (CNNs) achieve great success in image proces…
We deal with the controllable person image synthesis task which aims to re-render a human from a reference image with explicit control over body pose and appearance. Observing that person images are highly structured, we propose to generate desired images by extracting and distributing semantic enti…
In point cloud compression, sufficient contexts are significant for modeling the point cloud distribution. However, the contexts gathered by the previous voxel-based methods decrease when handling sparse point clouds. To address this problem, we propose a multiple-contexts deep learning framework ca…
Transformers are now widely used in code representation, and several recent works further develop tree Transformers to capture the syntactic structure in source code. Specifically, novel tree positional encodings have been proposed to incorporate inductive bias into Transformer.In this work, we prop…
Optical flow estimation is a classical yet challenging task in computer vision. One of the essential factors in accurately predicting optical flow is to alleviate occlusions between frames. However, it is still a thorny problem for current top-performing optical flow estimation methods due to insuff…
"This paper researches the unexplored task-point cloud salient object detection (SOD). Differing from SOD for images, we find the attention shift of point clouds may provoke saliency conflict, i.e., an object paradoxically belongs to salient and non-salient categories. To eschew this issue, we prese…
Point clouds upsampling is a challenging issue to generate dense and uniform point clouds from the given sparse input. Most existing methods either take the end-to-end supervised learning based manner, where large amounts of pairs of sparse input and dense ground-truth are exploited as supervision i…
Visual-inertial odometry (VIO) aims to predict trajectory by ego- motion estimation. In recent years, end-to-end VIO has made great progress. However, how to handle visual and inertial measurements and make full use of the complementarity of cameras and inertial sensors remains a challenge. In the p…
Benchmark datasets have a significant impact on accelerating research in programming language tasks. In this paper, we introduce CodeXGLUE, a benchmark dataset to foster machine learning research for program understanding and generation. CodeXGLUE includes a collection of 10 tasks across 14 datasets…
Learning distributed representation of source code requires modelling its syntax and semantics. Recent state-of-the-art models leverage highly structured source code representations, such as the syntax trees and paths therein. In this paper, we investigate two representative path encoding methods sh…
We propose a multi-task learning neural network for No-Reference image quality assessment (NR-IQA). The pro-posed architecture consists of a backbone feature extractor, a nested multi-task generative module and a quality regression module. We adopt a coarse-to-fine strategy to predict objective erro…
Generating portrait images by controlling the motions of existing faces is an important task of great consequence to social media industries. For easy use and intuitive control, semantically meaningful and fully disentangled parameters should be used as modifications. However, many existing techniqu…
This paper observes that there is an issue of high frequencies missing in the discriminator of standard GAN, and we reveal it stems from downsampling layers employed in the network architecture. This issue makes the generator lack the incentive from the discriminator to learn high-frequency content…
A long-cherished vision in robotics is to equip robots with skills that match the versatility and precision of humans. For example, when playing table tennis, a robot should be capable of returning the ball in various ways while precisely placing it at the desired location. A common approach to mod…
Pose-guided virtual try-on task aims to modify the fashion item based on pose transfer task. These two tasks that belong to person image synthesis have strong correlations and similarities. However, existing methods treat them as two individual tasks and do not explore correlations between them. Mor…
Traditional video quality assessment (VQA) methods evaluate localized picture quality and video score is predicted by temporally aggregating frame scores. However, video quality exhibits different characteristics from static image quality due to the existence of temporal masking effects. In this pap…
Pose-guided person image generation is to transform a source person image to a target pose. This task requires spatial manipulations of source data. However, Convolutional Neural Networks are limited by the lack of ability to spatially transform the inputs. In this paper, we propose a differentiable…
The Boolean satisfiability problem (SAT) is a famous NP-complete problem in computer science. An effective way for solving a satisfiable SAT problem is the stochastic local search (SLS). However, in this method, the initialization is assigned in a random manner, which impacts the effectiveness of SL…
Generic object detection algorithms have proven their excellent performance in recent years. However, object detection on underwater datasets is still less explored. In contrast to generic datasets, underwater images usually have color shift and low contrast; sediment would cause blurring in underwa…
Action classification combined with location regression is a widely-utilized mechanism in existing temporal action detection methods. However, there exists an inconsistency problem between locations and categories of action instances in this mechanism. More specifically, while the location of the pr…
Graph convolutional networks (GCNs) are potentially short of the ability to learn hierarchical representation for graph embedding, which holds them back in the graph classification task. Here, we propose AttPool, which is a novel graph pooling module based on attention mechanism, to remedy the probl…
Despite tremendous progress achieved in temporal action detection, state-of-the-art methods still suffer from the sharp performance deterioration when localizing the starting and ending temporal action boundaries. Although most methods apply boundary regression paradigm to tackle this problem, we ar…
Temporal action detection in untrimmed videos is an important yet challenging task. How to locate complex actions accurately is still an open question due to the ambiguous boundaries between action instances and the background. Recently a newly proposed work exploits Structured Segment Networks (SSN…
Code summarization (CS) and code generation (CG) are two crucial tasks in the field of automatic software development. Various neural network-based approaches are proposed to solve these two tasks separately. However, there exists a specific intuitive correlation between CS and CG, which has not bee…
Video anomaly detection under weak labels is formulated as a typical multiple-instance learning problem in previous works. In this paper, we provide a new perspective, i.e., a supervised learning task under noisy labels. In such a viewpoint, as long as cleaning away label noise, we can directly appl…
Recent advances of image-to-image translation focus on learning the one-to-many mapping from two aspects: multi-modal translation and multi-domain translation. However, the existing methods only consider one of the two perspectives, which makes them unable to solve each other's problem. To address t…
Cross-modal retrieval has been recently proposed to find an appropriate subspace where the similarity among different modalities, such as image and text, can be directly measured. In this paper, we propose Multi-step Self-Attention Network (MSAN) to perform cross-modal retrieval in a limited text sp…
In order to balance the detection time and accuracy, the state-of-the-art region-based detectors use a fixed number of proposals to obtain detection results in the inference phase. However, in surveillance scenes, object population varies in different images, causing the fixed proposal number become…
Image inpainting techniques have shown significant improvements by using deep neural networks recently. However, most of them may either fail to reconstruct reasonable structures or restore fine-grained textures. In order to solve this problem, in this paper, we propose a two-stage model which split…
This paper addresses the question: In neural dialog systems, why do sequence-to-sequence (Seq2Seq) neural networks generate short and meaningless replies for open-domain response generation? We conjecture that in a dialog system, due to the randomness of spoken language, there may be multiple equall…
Merge prediction is a practical inter-technique in HEVC, which can significantly improve the coding efficiency, especially for homogeneous regions in video sequences. In this paper, a motion aided merge mode (MAMM) is proposed to achieve a better trade-off between the prediction accuracy and bit rat…
Single materials have colors which form straight lines in RGB space. However, in severe shadow cases, those lines do not intersect the origin, which is inconsistent with the description of most literature. This paper is concerned with the detection and correction of the offset between the intersecti…
Road detection, which brings a visual perceptive ability to vehicles, is essential to build driver assistance systems. To help detect lane markings in challenging scenarios, one-time calibration of inverse perspective mapping (IPM) parameters is employed to build a bird's eye view of the road image.…