15 accepted papers
Mixture-of-Experts (MoE) architectures have recently become a more prevalent choice for large language models (LLMs) than dense architectures due to their superior performance. However, billions of parameters bring MoE LLMs a huge cost for deployment and inference. To address these issues, knowledge
Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision--language tasks. However, their capabilities remain unclear in relational-diagram (RD) reasoning, where correct answers must satisfy diagram-defined constraints such as directed dependencies, branchin
We present a feed-forward human performance capture method that renders novel views of a performer from a monocular RGB stream. A key challenge in this setting is the lack of sufficient observations, especially for unseen regions. Assuming the subject moves continuously over time, we take advantage…
Mixture of experts (MoE) dynamically routes inputs to specialized expert networks to scale model capacity with low inference overhead. However, the excessive parameter growth in MoE models poses challenges in low-resource settings. To address these issues, MoE with parameter-efficient fine-tuning (P
Vision-Language-Action models (VLAs) are emerging as powerful tools for learning generalizable visuomotor control policies. However, current VLAs are mostly trained on large-scale image–text–action data and remain limited in two key ways: (i) they struggle with pixel-level scene understanding, and (…
Parameter Efficient Fine-Tuning (PEFT) is a key technique for adapting a large pretrained model to downstream tasks by fine-tuning only a small number of parameters. Recent methods based on Fourier transforms have further reduced the fine-tuned parameters scale by only fine-tuning a few spectral coe
Maintaining visual separation is crucial to achieving safe and seamless high-density operation of airborne vehicles in shared airspace, where pilots currently shoulder this responsibility. To automate this, we present ViSafe, a high-speed airborne vision-only collision avoidance system. Designed un…
Prompt optimization aims to construct effective prompts to fully leverage the capabilities of large language models (LLMs). The key challenge lies in analyzing the outputs of LLMs, identifying fine-grained errors as explicit evidence and guiding reverse prompt correction. However, existing dominant…
Robust depth perception in visually-degraded environments is crucial for autonomous aerial systems. Thermal imaging cameras, which capture infrared radiation, are robust to visual degradation. However, due to lack of a large-scale dataset, the use of thermal cameras for uncrewed aerial system (UAS)
Simulation-based reinforcement learning (RL) has significantly advanced humanoid locomotion tasks, yet direct real-world RL from scratch or starting from pretrained policies remains rare, limiting the full potential of humanoid robots. Real-world training, despite being crucial for overcoming the si…
Making multi-camera visual SLAM systems easier to set up and more robust to the environment is attractive for vision robots. Existing monocular and binocular vision SLAM systems have narrow sensing Field-of-View (FoV), resulting in degenerated accuracy and limited robustness in textureless environme
Visual imitation learning methods demonstrate strong performance, yet they lack generalization when faced with visual input perturbations like variations in lighting and textures. This limitation hampers their practical application in real-world settings. To address this, we propose ***Stem-OB*** th…
Image quantization is a crucial technique in image generation, aimed at learning a codebook that encodes an image into a discrete token sequence. Recent advancements have seen researchers exploring learning multi-modal codebook (i.e., text-aligned codebook) by utilizing image caption semantics, aimi…
Vector-Quantized Image Modeling (VQIM) is a fundamental research problem in image synthesis which aims to represent an image with a discrete token sequence. Existing studies effectively address this problem by learning a discrete codebook from scratch and in a code-independent manner to quantize con…
We present a Visual-Inertial Odometry (VIO) algorithm with multiple non-overlapping monocular cameras aiming at improving the robustness of the VIO algorithm. An initialization scheme and tightly-coupled bundle adjustment for multiple non-overlapping monocular cameras are proposed. With more stable…