Found 62 document(s)
Page 2 of 5
-
Quantization-aware training (QAT) aims to recover reasoning capabilities in low-bit large language models (LLMs). Existing recipes typically supervise the quantized student with the original full-precision model on fixed...
-
Recently, multi-node inertial measurement unit (multi-IMU) systems have shown promise for robust odometry in legged robots. Multi-IMU fusion can improve legged robot odometry but requires accurate spatiotemporal calibrat...
-
Signed graph learning has emerged as a powerful framework for modeling networks with both positive and negative interactions. While graph-filter-based methods have achieved promising empirical performance on signed netwo...
-
Recent advances in foundation-model agents have enabled increasingly capable embodied systems for long-horizon planning and interaction. However, embodied agents require fast, closed-loop decisions as they continuously p...
-
Relighting and novel view synthesis of human portraits are essential in applications such as portrait photography, virtual reality (VR), and augmented reality (AR). Despite recent progress, 3D-aware portrait relighting r...
-
Quantum key distribution (QKD), whose security is derived from quantum mechanics rather than computational assumptions, is moving into standardization and commercial deployment. Yet its security guarantees rest on techni...
-
World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interaction requires separate evidence about action selecti...
-
We envision a general-purpose protein foundation model as a unified, interactive model of sequence, structure, and function, capable of understanding, generation, and cross-modal translation while retaining the instructi...
-
This paper introduces Spark-Audio 1.0, a speech foundation model trained on domestically produced computing infrastructure. The model accepts text and speech inputs and generates text outputs. It supports multilingual (9...
-
Text-to-image (T2I) models have achieved remarkable progress in image quality and instruction following, prompting growing research interest in their capacity for deep understanding that goes beyond literal prompt matchi...
-
Visual grounding with vision-language models such as CLIP typically produces a single deterministic relevance map for an image-query pair, without indicating whether the localisation is reliable or whether the referent i...
-
Invasive computing is a paradigm for designing and programming future parallel computing systems. For systems with 1,000 or more cores on a chip, resource-aware programming is of utmost importance to obtain high utilisat...
-
Robot tasks require grounding spatial language in physical scenes, but task success alone cannot establish whether spatial instructions are followed. We present BEHAVIOR-Spatial, a benchmark built on BEHAVIOR-1K that mea...
-
Video diffusion models provide a source of interaction representations for robot control, but transferring these representations requires reconciling variable camera inputs with heterogeneous action interfaces and closed...