33 accepted papers
Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL) that reason and act in interactive environments. However, sparse and sometimes unverifiable rewards make it extremely challenging to assign credit when training LLM agents that serv…
Backdoor attacks embed malicious behaviors into Large Language Models (LLMs), enabling adversaries to trigger harmful outputs or bypass safety controls. However, the persistence of the implanted backdoors under user-driven post-deployment continual fine-tuning has been rarely examined. Most prior wo
The rapid advancement of Large Multimodal Models (LMMs) for 2D images and videos has sparked interest in extending these models to 3D scenes, with the goal of human-like visual-spatial intelligence. However, achieving deep spatial understanding comparable to human capabilities remains challenging fo
Large Language Models (LLMs) have shown impressive reasoning capabilities in well-defined problems with clear solutions, such as mathematics and coding. However, they still struggle with complex real-world scenarios like business negotiations, which require strategic reasoning—an ability to navigate…
Recent advancements in image generation models enable the creation of high-quality images and targeted modifications based on textual instructions. Some models even support multimodal complex guidance and demonstrate robust task generalization capabilities. However, they still fall short of meeting…
Human preference alignment is critical in building powerful and reliable large language models (LLMs). However, current methods either ignore the multi-dimensionality of human preferences (e.g. helpfulness and harmlessness) or struggle with the complexity of managing multiple reward models. To addre…
Reconstructing 3D scenes from a single image is a fundamentally ill-posed task due to the severely under-constrained nature of the problem. Consequently, when the scene is rendered from novel camera views, particularly in unseen regions far away from the input camera, existing single image to 3D rec…
Parameter sharing is a common strategy in multi-agent reinforcement learning (MARL) to make the training more efficient and scalable. However, applying parameter sharing among agents indiscriminately hinders the emergence of agents diversity and degrades the final cooperative performance. To better…
Backdoor attacks in reinforcement learning (RL) have previously employed intense attack strategies to ensure attack success. However, these methods suffer from high attack costs and increased detectability. In this work, we propose a novel approach, BadRL, which focuses on conducting highly sparse b…
Labelling LiDAR point clouds for training autonomous driving is extremely expensive and difficult. LiDAR simulation aims at generating realistic LiDAR data with labels for training and verifying self-driving algorithms more efficiently. Recently, Neural Radiance Fields (NeRF) have been proposed for…
Exploration under sparse rewards is a key challenge for multi-agent reinforcement learning problems. Although population-based learning shows its potential in producing diverse behaviors, most previous works still focus on improving the exploration of a single joint policy. In this paper, we show th…
Decision making demands intricate interplay between perception, memory, and reasoning to discern optimal policies. Conventional approaches to decision making face challenges related to low sample efficiency and poor generalization. In contrast, foundation models in language and vision have showcased…
Building agents with adaptive behavior in cooperative tasks stands as a paramount goal in the realm of multi-agent systems. Current approaches to developing cooperative agents rely primarily on learning-based methods, whose policy generalization depends heavily on the diversity of teammates they int…
Multi-Agent Policy Gradient (MAPG) has made significant progress in recent years. However, centralized critics in state-of-the-art MAPG methods still face the centralized-decentralized mismatch (CDM) issue, which means sub-optimal actions by some agents will affect other agent's policy learning. Whi…
Continual learning (CL) aims to enable a model to retain knowledge of old tasks while learning new ones. One effective approach to CL is based on data rehearsal method. However, this approach increases the cost of storing data and cannot be used when data from old tasks is unavailable for some reaso…
Exploration under sparse rewards is a key challenge for multi-agent reinforcement learning problems. Previous works argue that complex dynamics between agents and the huge exploration space in MARL scenarios amplify the vulnerability of classical count-based exploration methods when combined with ag…
Despite the dramatic success in image generation, Generative Adversarial Networks (GANs) still face great challenges in text generation. The difficulty in generator training arises from the limited representation capacity and uninformative learning signals obtained from the discriminator. In this wo…
Neural Radiance Fields (NeRFs) aim to synthesize novel views of objects and scenes, given the object-centric camera views with large overlaps. However, we conjugate that this paradigm does not fit the nature of the street views that are collected by many self-driving cars from the large-scale unboun…
Exploration under sparse rewards is a key challenge for multi-agent reinforcement learning problems. One possible solution to this issue is to exploit inherent task structures for an acceleration of exploration. In this paper, we present a novel exploration approach, which encodes a special structur…
We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting. The key idea lies in the coordinated adaptation of step size during the policy update process among multiple agents. We prove the monoton…
Generative Adversarial Networks (GANs) have achieved great success in image synthesis, but have proven to be difficult to generate natural language. Challenges arise from the uninformative learning signals passed from the discriminator. In other words, the poor learning signals limit the learning ca…
Model-based reinforcement learning (RL) is more sample efficient than model-free RL by using imaginary trajectories generated by the learned dynamics model. When the model is inaccurate or biased, imaginary trajectories may be deleterious for training the action-value and policy functions. To allevi…
Vision transformers (ViTs) have pushed the state-of-the-art for various visual recognition tasks by patch-wise image tokenization followed by self-attention. However, the employment of self-attention modules results in a quadratic complexity in both computation and memory usage. Various attempts on…
Finding views with a good composition from an input image is a common but challenging problem. There are usually at least dozens of candidates (regions) in an image, and how to evaluate these candidates is subjective. Most existing methods only use the feature corresponding to each candidate to eval…
Image cropping aims at improving the framing of an image by removing its extraneous outer areas, which is widely used in the photography and printing industry. In some cases, the aspect ratio of cropping results is specified depending on some conditions. In this paper, we propose a meta-learning (le…
Human can well recognize images of novel categories just after browsing few examples of these categories. One possible reason is that they have some external discriminative visual information about these categories from their prior knowledge. Inspired from this, we propose a novel Knowledge Transfer…
In this paper, we aim at automatically searching an efficient network architecture for dense image prediction. Particularly, we follow the encoder-decoder style and focus on designing a connectivity structure for the decoder. To achieve that, we design a densely connected network with learnable conn…
To recognize objects of the unseen classes, most existing Zero-Shot Learning (ZSL) methods first learn a compatible projection function between the common semantic space and the visual space based on the data of source seen classes, then directly apply it to the target unseen classes. However, in re…
Image cropping aims at improving the aesthetic quality of images by adjusting their composition. Most weakly supervised cropping methods (without bounding box supervision) rely on the sliding window mechanism. The sliding window mechanism requires fixed aspect ratios and limits the cropping region w…
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space between image and semantic representations. For years, among existing works, it has been the center task to learn the proper mapping matrices aligning the visual and semantic space, whilst the importanc…
Image processing and pixel-wise dense prediction have been advanced by harnessing the capabilities of deep learning. One central issue of deep learning is the limited capacity to handle joint upsampling. We present a deep learning building block for joint upsampling, namely guided filtering layer. T…
Occlusion is a main challenge for human pose estimation, which is largely ignored in popular tree structure models. The tree structure model is simple and convenient for exact inference, but short in modeling the occlusion coherence especially in the case of self-occlusion. We propose an occlusion a…
Markov Random Field (MRF) is an important tool and has been widely used in many vision tasks. Thus, the optimization of MRFs is a problem of fundamental importance. Recently, Veskler and Kumar et. al propose the range move algorithms, which are one of the most successful solvers to this problem. How…