3 papers
cs.CV2026
InteracVid: Building a Real Interactive Audio-Visual Response Dataset from Live-Chat Videos
Chi Zhang, Haoyang Shi, Yueyi Liu +4
Large language models have made text the default medium for human--AI interaction, buttext alone cannot express the full range of responses required by multimodal assistants,avatar…
cs.CV2026
Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning
Jiacheng Hua, Yishu Yin, Yuhang Wu +3
Existing Multimodal Large Language Models (MLLMs) struggle with 3D spatial reasoning, as they fail to construct structured abstractions of the 3D environment depicted in video inpu…
cs.LG2026
GreedySnake: Accelerating SSD-Offloaded LLM Training with Efficient Scheduling and Optimizer Step Overlapping
Yishu Yin, Xuehai Qian
SSD-offloaded training offers a practical and promising approach to making LLM training cost-effective. Building on gradient accumulation with micro-batches, this paper introduces…