45 accepted papers
Reinforcement Learning (RL) has shown remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). Process-Supervised RL (PSRL) has emerged as a more effective paradigm compared to outcome-based RL. However, existing PSRL approaches suffer from limited exploration effi…
Parameter-Efficient finetuning (PEFT) enhances model performance on downstream tasks by updating a minimal subset of parameters. Representation finetuning (ReFT) methods further improve efficiency by freezing model weights and optimizing internal representations with fewer parameters than PEFT, outp
The dominant paradigm for training Large Vision-Language Models (LVLMs) in navigation relies on imitating expert trajectories. This approach reduces the complex navigation task to a sequence-to-sequence replication of a single correct path, fundamentally limiting the agent's ability to explore and g…
Three-dimensional molecular representation learning has shown great promise in modeling chemical structures and their properties. However, most existing approaches implicitly assume molecules are at or near equilibrium states. This assumption breaks down for non-equilibrium structures--ubiquitous in
The impressive performance of large language models (LLMs) also brings inherent toxicity risks, prompting the need for effective detoxification to support responsible deployment. Prevailing methods generally follow an inflexible model-specific fashion, addressing only individual models or model fami
Recent advancements in Large Language Models (LLMs) have shown that it is promising to utilize Process Reward Models (PRMs) as verifiers to enhance the performance of LLMs. However, current PRMs face three key challenges: (1) limited process supervision and generalization capabilities, (2) dependenc
High-fidelity text-to-image and text-to-video generation typically relies on Classifier-Free Guidance (CFG), but achieving optimal results often demands computationally expensive sampling schedules. In this work, we propose MAMBO-G, a training-free acceleration framework that significantly reduces c…
Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). While automated methods have improved scalability, existing approaches often rely on static heuristics or stochastic search, rendering them brittle against advanced safety alignment. To address this, we introduce…
Large language model (LLM) alignment faces a critical dilemma when addressing multiple human preferences: improvements in one dimension frequently come at the expense of others, creating unavoidable trade-offs between competing objectives like helpfulness and harmlessness. While prior work mainly fo…
Bio-inspired aquatic propulsion offers high thrust and maneuverability but is prone to destabilizing forces such as lift fluctuations, which are further amplified by six-degree-of-freedom (6-DoF) fluid coupling. We formulate quadrupedal swimming as a constrained optimization problem that maximizes f…
Real-world language agents must handle complex, multi-step workflows across diverse applications. For instance, an agent may manage emails by coordinating with calendars and file systems, or monitor a production database like BigQuery to detect anomalies and generate reports following a standard ope…
Multimodal Large Language Models (MLLMs) are susceptible to the implicit reasoning risk, wherein innocuous unimodal inputs synergistically assemble into risky multimodal data that produce harmful outputs. We attribute this vulnerability to the difficulty of MLLMs maintaining safety alignment through
Robot-assisted dressing is a popular but challenging topic in the field of robotic manipulation, offering significant potential to improve the quality of life for individuals with mobility limitations. Currently, the majority of research on robot-assisted dressing focuses on how to put on loose-fitt
Composed Image Retrieval (CIR) is a multi-modal task that seeks to retrieve target images by harmonizing a reference image with a modified instruction. A key challenge in CIR lies in compositional conflicts between the reference image (e.g., blue, long sleeve) and the modified instruction (e.g., gre…
Humans excel at understanding and reasoning about novel, compositionally structured knowledge, largely due to their capacity for compositional generalization—a cognitive skill that has recently been validated in structured neural networks. However, most existing research has focused primarily on sem…
Data scarcity in offline multi-agent reinforcement learning (MARL) is a key challenge for real-world applications. Recent advances in offline single-agent reinforcement learning (RL) demonstrate the potential of data synthesis to mitigate this issue. However, in multi-agent systems, interactions bet…
Unmanned Aerial Vehicles (UAVs) are widely adopted across various fields, yet they raise significant privacy and safety concerns, demanding robust monitoring solutions. Existing anti-UAV methods primarily focus on position tracking but fail to capture UAV behavior and intent. To address this, we int…
Deep visual odometry has demonstrated great advancements by learning-to-optimize technology. This approach heavily relies on the visual matching across frames. However, ambiguous matching in challenging scenarios leads to significant errors in geometric modeling and bundle adjustment optimization,…
Generating cell-level descriptions for Jupyter Notebooks, which is a major resource consisting of codes, tables, and descriptions, has been attracting increasing research attention. However, existing methods for Jupyter Notebooks mostly focus on generating descriptions from code snippets or table ou…
Modern deep architectures often rely on large-scale datasets, but training on these datasets incurs high computational and storage overhead. Real-world datasets often contain substantial redundancies, prompting the need for more data-efficient training paradigms. Data selection has shown promise to…
Text-to-motion generation, which translates textual descriptions into human motions, has been challenging in accurately capturing detailed user-imagined motions from simple text inputs. This paper introduces StickMotion, an efficient diffusion-based network designed for multi-condition scenarios, wh…
Deep Reinforcement Learning (DRL) agents have demonstrated impressive success in a wide range of game genres. However, existing research primarily focuses on optimizing DRL competence rather than addressing the challenge of prolonged player interaction. In this paper, we propose a practical DRL agen…
Spatio-temporal (ST) prediction has garnered a De facto attention in earth sciences, such as meteorological prediction, human mobility perception. However, the scarcity of data coupled with the high expenses involved in sensor deployment results in notable data imbalances. Furthermore, models that a…
"Data augmentation (DA) has been widely used to improve the generalization of deep neural networks. While existing DA methods have proven effective, they often rely on augmentation operations with random magnitudes to each sample. However, this approach can inadvertently introduce noise, induce dist…
Deep learning-based image stitching pipelines are typically divided into three cascading stages: registration, fusion, and rectangling. Each stage requires its own network training and is tightly coupled to the others, leading to error propagation and posing significant challenges to parameter tunin…
Data augmentation has been widely used in low-resource NER tasks to tackle the problem of data sparsity. However, previous data augmentation methods have the disadvantages of disrupted syntactic structures, token-label mismatch, and requirement for external knowledge or manual effort. To address the…
Predicting human pose sequences via existing pose estimators often encounters various estimation errors. Motion refinement methods aim to optimize the predicted human pose sequences from pose estimators while ensuring minimal computational overhead and latency. Prior investigations have primarily co…
Most existing RGB-T tracking networks extract modality features in a separate manner, which lacks interaction and mutual guidance between modalities. This limits the network's ability to adapt to the diverse dual-modality appearances of targets and the dynamic relationships between the modalities. A…
Keypoint-based representation has proven advantageous in various visual and robotic tasks. However, the existing 2D and 3D methods for detecting keypoints mainly rely on geometric consistency to achieve spatial alignment, neglecting temporal consistency. To address this issue, the Transporter method…
In conventional recognition tasks, models are only trained to recognize learned targets, but it is usually difficult to collect training examples of all potential categories. In the testing phase, when models receive test samples from unknown classes, they mistakenly classify the samples into known…
Cooperative multi-agent reinforcement learning (MARL) is a challenging task, as agents must learn complex and diverse individual strategies from a shared team reward. However, existing methods struggle to distinguish and exploit important individual experiences, as they lack an effective way to deco…
The existing one-stage multi-object tracking (MOT) algorithms have achieved satisfactory performance benefiting from a large amount of labeled data. However, acquiring plenty of laborious annotated frames is not practical in real applications. To reduce the cost of human annotations, we propose Hete…
Neural Architecture Search (NAS) has been increasingly appealing to the society of object Re-Identification (ReID), for that task-specific architectures significantly improve the retrieval performance. Previous works explore new optimizing targets and search spaces for NAS ReID, yet they neglect the…
This work presents two astonishing findings on neural networks learned for large-scale image classification. 1) Given a well-trained model, the logits predicted for some category can be directly obtained by linearly combining the predictions of a few other categories, which we call neural dependency…
Cooperative multi-agent reinforcement learning (MARL) has made prominent progress in recent years. For training efficiency and scalability, most of the MARL algorithms make all agents share the same policy or value network. However, in many complex multi-agent tasks, different agents are expected to…
The key challenge of zero-shot learning (ZSL) is how to infer the latent semantic knowledge between visual and attribute features on seen classes, and thus achieving a desirable knowledge transfer to unseen classes. Prior works either simply align the global features of an image with its associated…
"Object detection using single point supervision has received increasing attention over the years. However, the performance gap between point supervised object detection (PSOD) and bounding box supervised detection remains large. In this paper, we attribute such a large performance gap to the failur…
Generative methods have been successfully applied in zero-shot learning (ZSL) by learning an implicit mapping to alleviate the visual-semantic domain gaps and synthesizing unseen samples to handle the data imbalance between seen and unseen classes. However, existing generative methods simply use vis…
The existing multi-person absolute 3D pose estimation methods are mainly based on two-stage paradigm, i.e., top-down or bottom-up, leading to redundant pipelines with high computation cost. We argue that it is more desirable to simplify such two-stage paradigm to a single-stage one to promote both e…
Image animation brings life to the static object in the source image according to the driving video. Recent works attempt to perform motion transfer on arbitrary objects through unsupervised methods without using a priori knowledge. However, it remains a significant challenge for current unsupervise…
Unsupervised domain adaptation (UDA) in the task of person re-identification (re-ID) is highly challenging due to large domain divergence and no class overlap between domains. Pseudo-label based self-training is one of the representative techniques to address UDA. However, label noise caused by unsu…
This paper proposes a novel Dynamic Conditional Convolutional Network (DCCN) to handle conditional few-shot learning, i.e, only a few training samples are available for each condition. DCCN consists of dual subnets: DyConvNet contains a dynamic convolutional layer with a bank of basis filters; Condi…
Pose variation is one key challenge in face recognition. As opposed to current techniques for pose invariant face recognition, which either directly extract pose invariant features for recognition, or first normalize profile face images to frontal pose before feature extraction, we argue that it is…
In this paper, we propose a novel weakly supervised model, Multi-scale Anchored Transformer Network (MATN), to accurately localize free-form textual phrases with only image-level supervision. The proposed MATN takes region proposals as localization anchors, and learns a multi-scale correspondence ne…
Synthesizing realistic profile faces is promising for more efficiently training deep pose-invariant models for large-scale unconstrained face recognition, by populating samples with extreme poses and avoiding tedious annotations. However, learning from synthetic faces may not achieve the desired pe…