16 accepted papers
Unified conditional image generation remains difficult because different tasks depend on fundamentally different internal representations. Some require conceptual understanding for semantic synthesis, while others rely on localization cues for spatial precision. Forcing these heterogeneous tasks to
Recent Progress in post-training flow matching for text-to-image (T2I) generation with Group Relative Policy Optimization (GRPO) has demonstrated strong potential. However, it is hindered by a critical limitation: inaccurate advantage attribution. In this work, we argue that aggregating consecutive …
Alignment of large language models (LLMs) with human values has recently garnered significant attention, with prominent examples including the canonical yet costly Reinforcement Learning from Human Feedback (RLHF) and the simple Direct Preference Optimization (DPO). In this work, we demonstrate that…
Employing Multimodal Large Language Models (MLLMs) for long video understanding remains a challenging problem due to the dilemma between the substantial number of video frames (i.e., visual tokens) versus the limited context length of language models. Traditional uniform sampling often leads to sele…
The success of artificial neural networks (ANNs) hinges greatly on the judicious selection of an activation function, introducing non-linearity into network and enabling them to model sophisticated relationships in data. However, the search of activation functions has largely relied on empirical kno…
Floor plans serve as a graphical language through which architects sketch and communicate their design ideas. Actually, in the Architecture, Engineering, and Construction (AEC) design stages, generating floor plans is a complex task requiring domain expertise and alignment with user requirements. Ho…
Direct Preference Optimization (DPO) has recently expanded its successful application from aligning large language models (LLMs) to aligning text-to-image models with human preferences, which has generated considerable interest within the community. However, we have observed that these approaches re…
Implicit reward mechanism of Direct Preference Optimization (DPO) has facilitated its recent applications beyond large language models (LLMs), notably in aligning text-to-image models with human preferences. While promising results have been achieved with algorithms such as Diffusion-DPO, their reli…
Diffusion denoising models have great potential in generating diverse and realistic human motions. However, despite the impressive performance of existing methods, they still face some issues. The diffusion process often significantly overlooks physical laws, leading to physically implausible motion…
Direct Preference Optimization (DPO) has recently expanded its successful application beyond aligning large language models (LLMs), further targeting the alignment of text-to-image models with human preferences. However, traditional DPO approach would inadvertently result in a simultaneous reduction…
Reinforcement learning (RL) has garnered increasing attention in text-to-image (T2I) generation. However, most existing RL approaches are tailored to either diffusion models or autoregressive models, overlooking an important alternative: masked generative models. In this work, we propose Mask-GRPO,…
Offline reinforcement learning (RL) has shown great potential in many robotic tasks, where doing trial-and-error with the environment is risky, costly, or time-consuming. However, it is still hard to succeed in long-horizon tasks especially when given suboptimal and multimodal offline datasets. Neve
Offline reinforcement learning (RL) provides a promising approach to avoid costly online interaction with the real environment. However, the performance of offline RL highly depends on the quality of the datasets, which may cause extrapolation error in the learning process. In many robotic applicati…
Driven by the empirical success and wide use of deep neural networks, understanding the generalization performance of overparameterized models has become an increasingly popular question. To this end, there has been substantial effort to characterize the implicit bias of the optimization algorithms…
We study predictive control in a setting where the dynamics are time-varying and linear, and the costs are time-varying and well-conditioned. At each time step, the controller receives the exact predictions of costs, dynamics, and disturbances for the future $k$ time steps. We show that when the pre…
We study online convex optimization in a setting where the learner seeks to minimize the sum of a per-round hitting cost and a movement cost which is incurred when changing decisions between rounds. We prove a new lower bound on the competitive ratio of any online algorithm in the setting where the…