17 accepted papers
Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm limits their ability to handle complex prompts requiring iterative refinement. To enable multi-round Reflective Visual …
Recent advancements in end-to-end autonomous driving systems (ADSs) underscore their potential for perception and planning capabilities. However, challenges remain. Complex driving scenarios contain rich semantic information, yet ambiguous or noisy semantics can compromise decision reliability, whil
Mixture-of-Experts (MoE) is a sparse neural architecture that significantly increases model capacity while maintaining low computational complexity. However, deploying MoE-based large language models (LLMs) on memory-constrained edge devices remains challenging due to their substantial memory requir
Although Video Large Language Models (VLLMs) have shown remarkable capabilities in video understanding, they are required to process high volumes of visual tokens, causing significant computational inefficiency. Existing VLLMs acceleration frameworks usually compress spatial and temporal redundancy…
As the foundation of closed-loop training and evaluation in autonomous driving, traffic simulation still faces two fundamental challenges: covariate shift introduced by open-loop imitation learning and limited capacity to reflect the multimodal behaviors observed in real-world traffic. Although rece…
Long-context large language models (LLMs) are increasingly deployed in real-world applications, yet self-attention remains a major efficiency bottleneck -- especially during decoding -- due to the necessity of repeatedly processing ever-growing key-value (KV) caches. Existing sparse attention reduce…
Generating safety-critical scenarios, which are essential yet difficult to collect at scale, offers an effective method to evaluate the robustness of autonomous vehicles (AVs). Existing methods focus on optimizing adversariality while preserving the naturalness of scenarios, aiming to achieve a bala…
Pose graph optimization (PGO) is a fundamental technique for robot localization. It is typically encoded with a sparse graph. The recent work on the cycle-based PGO reveals the merits of solving PGOs in the graph cycle space, which brings the computation of the minimum cycle basis (MCB) into the rob
Recent studies have proven the strength of task-oriented point cloud sampling methods over traditional non-learned ones. However, previous task-oriented samplers are not adequate to extract local details and spatial patterns of point clouds, limiting the quality of synthesized points. In this paper,…
The conversational recommender system (CRS) aims to provide high-quality recommendations through interactive dialogues. However, previous CRS models have no effective mechanisms for task planning and topic elaboration, and thus they hardly maintain coherence in multi-task recommendation dialogues. I…
Movie highlights stand out of the screenplay for efficient browsing and play a crucial role on social media platforms. Based on existing efforts, this work has two observations: (1) For different annotators, labeling highlight has uncertainty, which leads to inaccurate and time-consuming annotations…
Realistic human-centric rendering plays a key role in both computer vision and computer graphics. Rapid progress has been made in the algorithm aspect over the years, yet existing human-centric rendering datasets and benchmarks are rather impoverished in terms of diversity (e.g., outfit's fabric/mat…
Temporal video segmentation is the get-to-go automatic video analysis, which decomposes a long-form video into smaller components for the following-up understanding tasks. Recent works have studied several levels of granularity to segment a video, such as shot, event, and scene. Those segmentations…
A long-term video, such as a movie or TV show, is composed of various scenes, each of which represents a series of shots sharing the same semantic story. Spotting the correct scene boundary from the long-term video is a challenging task, since a model must understand the storyline of the video to fi…
Generating high-fidelity talking head video by fitting with the input audio sequence is a challenging problem that receives considerable attentions recently. In this paper, we address this problem with the aid of neural scene representation networks. Our method is completely different from existing…
The facial expression analysis requires a compact and identity-ignored expression representation. In this paper, we model the expression as the deviation from the identity by a subtraction operation, extracting a continuous and identity-invariant expression embedding. We propose a Deviation Learning…
In this paper, we present a novel strategy to design disentangled 3D face shape representation. Specifically, a given 3D face shape is decomposed into identity part and expression part, which are both encoded and decoded in a nonlinear way. To solve this problem, we propose an attribute decompositio…