13 accepted papers
As video content creation shifts towards long-form narratives, retrieving and composing short clips into coherent storylines becomes a critical challenge. Standard retrieval formulations, however, perform context-agnostic retrieval, prioritizing local semantic alignment while neglecting procedural s…
This paper provides a simplification on OpenVision's architecture and loss design for enhancing its training efficiency. Following the prior vision-language pretraining works CapPa and AIMv2, as well as modern multimodal designs like LLaVA, our changes are straightforward: we remove the text encoder
This paper introduces STAR-1, a high-quality, just-1k-scale safety dataset specifically designed for large reasoning models (LRMs) like DeepSeek-R1. Built on three core principles --- diversity, deliberative reasoning, and rigorous filtering --- STAR-1 aims to address the critical needs for safety a
We present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for vector quantization, which is typically designed for audio co…
OpenAI's CLIP models, released in early 2021, have long been the only viable choice for the research community in building multimodal foundation models. This dominance has only recently been challenged by a few alternatives like SigLIP. However, to the best of our knowledge, all these solutions are…
Accurate localization for intelligent robots remains a significant challenge, and self-supervised visual-inertial odometry (VIO) has emerged as a promising solution. However, existing self-supervised VIO works consider inertial information as the ordinary data input, losing its ability to recover ab
Dataset distillation aims to synthesize small datasets with little information loss from original large-scale ones for reducing storage and training costs. Recent state-of-the-art methods mainly constrain the sample synthesis process by matching synthetic images and the original ones regarding gradi…
In this paper, we propose a fast extrinsic calibration method for fusing multiple inertial measurement units (MIMU) to improve visual-inertial odometry (VIO) localization accuracy. Currently, data fusion algorithms for MIMU highly depend on the number of inertial sensors. Based on the assumption tha…
We previously proposed contextual spelling correction (CSC) to correct the output of end-to-end (E2E) automatic speech recognition (ASR) models with contextual information such as name, place, etc. Although CSC has achieved reasonable improvement in the biasing problem, there are still two drawbacks…
Recovering depth information from a single image is a long-standing challenge, and self-supervised depth estimation methods have gradually attracted attention due to not relying on high-cost ground truth. Constructing an accurate photometric loss based on photometric consistency is crucial for these…
Custom voice, a specific text to speech (TTS) service in commercial speech platforms, aims to adapt a source TTS model to synthesize personal voice for a target speaker using few speech from her/him. Custom voice presents two unique challenges for TTS adaptation: 1) to support diverse customers, the…
Learning to distinguish independent moving objects from the observed optical flow with a moving camera remains challenging. In this work, we first present a novel camera pose compensation (CPC) scheme. With the help of ingenious geometric analysis, it breaks the observed optical flow into patterns t…
Recent CNN-based optical flow approaches have a separated structure of feature extraction and flow estimation. The core task of optical flow is finding the corresponding points while rich representation is just the key part of such matching problems. However, the prior work usually pays more attenti…