11 accepted papers
Large language models (LLMs) are increasingly used as automatic evaluators of generative AI outputs, a paradigm often referred to as "LLM-as-a-judge." In practice, LLM judges are imperfect predictions for the underlying truth and can exhibit systematic, non-random errors. Two main approaches have re…
As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing approaches remain limited: full trajectories are often too context-specific to transfer, while tool-level reuse ignores the c…
State-of-the-art text-to-image diffusion models (DMs) achieve remarkable quality, yet their massive parameter scale (8-11B) poses significant challenges for inferences on resource-constrained devices. In this paper, we present HierarchicalPrune, a novel compression framework grounded in a key observ
Deep multi-modal clustering fully learns semantically consistent and discriminative cluster representations between multiple modalities in an unlabeled manner. However, existing methods treat all samples equally, ignoring varying sample quality, which limits clustering performance. Inspired by the c
Embodied Question Answering (EQA) is a task in artificial intelligence where an intelligent agent is required to answer questions about its environment. For example, to answer a question such as "Is the TV on or off?", the agent must navigate to the room with the TV and answer with either "On." or "…
The control of locomotion in walking robots with various architectural designs presents significant challenges. While existing approaches primarily rely on low-level state information and isolated visual features, lacking the high-level semantic understanding that humans use to reason about movement
In the scope of 3D human pose estimation, the task encompasses estimating the 3D positions of key skeletal points (i.e., wrists, elbows, and knees) from a 2D image or video sequence. This technology demonstrates widespread applicability across diverse domains, encompassing domains such as kinematic…
Reward acts as a signal to guide the agent’s learning process in Reinforcement Learning (RL), evaluating and assigning rewards to the agent’s actions based on theiralignment with goals. Designing reward is challenging in multiagent environment such as StarCraft II benchmark since agents face credit…
Mixture models serve as one fundamental tool with versatile applications. However, their training techniques, like the popular Expectation Maximization (EM) algorithm, are notoriously sensitive to parameter initialization and often suffer from bad local optima that could be arbitrarily worse than th…
Due to the success of large-scale visual-language pretraining (VLP) models and the widespread use of image-text retrieval in industry areas, it is now critically necessary to reduce the model size and streamline their mobile-device deployment. Single- and dual-stream model structures are commonly us…
Classically, statistical datasets have a larger number of data points than features ($n > p$). The standard model of classical statistics caters for the case where data points are considered conditionally independent given the parameters. However, for $n \approx p$ or $p > n$ such models are poorly…