Bridging Short Videos and Live Streams: Reasoning-Guided Multimodal LLMs for Cross-Domain Representation Learning

• URL: http://arxiv.org/abs/2606.04448v1
• Date: Wed, 03 Jun 2026 04:49:01 GMT
• Title: Bridging Short Videos and Live Streams: Reasoning-Guided Multimodal LLMs for Cross-Domain Representation Learning
• Abstract summary: Reasoning-Guided Cross-Domain Representation Learning (RGCD-Rep)<n>RGCD-Rep is a reasoning-guided framework for cross-domain recommendation from short videos to live streams.<n>It is fully deployed and serves over 400 million users daily.
• Score: 38.08336224801579
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As live streaming services grow, many platforms offer short videos and live streams to meet diverse needs. Short videos carry substantial traffic and rich behavior signals, whereas live streaming is a core conversion scenario with sparse behavior data, making cold start severe. Transferring user interests from short videos to live streaming recommendation can alleviate these issues. Meanwhile, short videos and live streams are complex multimodal items, and integrating multimodal signals improves recommendation performance. Although Multimodal Large Language Models (MLLMs) show strong multimodal understanding and reasoning, their application to cross-domain recommendation remains underexplored. To this end, we propose Reasoning-Guided Cross-Domain Representation Learning (RGCD-Rep), a reasoning-guided framework for cross-domain recommendation from short videos to live streams. RGCD-Rep introduces MLLM reasoning resource-efficiently and learns transferable item representations guided by behavioral collaboration via two-stage training. First, reasoning-aware distillation lets a frozen teacher MLLM generate structured cross-domain reasoning knowledge and distills it into a lightweight student MLLM. Second, transferability-guided cross-domain representation learning decomposes item representations into transferable and domain residual representations. The resulting representations are computed offline and integrated into downstream retrieval tasks, enabling low-cost industrial deployment. Extensive offline experiments demonstrate RGCD-Rep's superiority. After deployment in Kuaishou's live streaming recommendation system, A/B tests show significant gains across multiple core business metrics, confirming its effectiveness and practicality in real industrial scenarios. RGCD-Rep is fully deployed and serves over 400 million users daily.

Related papers

• Is Our Benchmark Enough? An Analysis of Continual Learning for MLLMs [4.1765120028423]
  Continual adaptation is essential for multimodal large language models (MLLMs) deployed across evolving domains.<n>This paper revisits this claim on the MLLM-CL benchmark and argues for two claims.<n>First, routing does not require an MLLM: a simple training-free, replay-free ptotypical routing method (textscRePRo) matches the MLLM-based router of MR-LoRA at far lower computational cost.<n>Second, shared experts do not improve continual learning for MLLMs, despite their theoretical appeal.
  arXiv  Detail & Related papers  (2026-06-18T21:58:05Z)
• InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning [61.87294123934038]
  We present InternVideo3, a framework enhancing multimodal understanding in video tasks.<n>MCR treats understanding as a closed-loop process over a shared, evolving context.<n>We show InternVideo3 achieves strong performance on benchmarks like Video-MME, MLVU, and Ego.
  arXiv  Detail & Related papers  (2026-06-10T15:17:08Z)
• Harnessing Streaming Video in the Wild [53.23721420272668]
  Vision-Language Models (VLMs) are increasingly required to process video streams in applications such as video-call assistants, live commentary, and embodied robots.<n>An ideal streaming system should support proactive interaction, long-horizon memory, and real-time processing.<n>ExistingVLMs excel at offline video understanding but fall short in streaming capabilities and lack dedicated infrastructure for streaming deployment.
  arXiv  Detail & Related papers  (2026-06-07T13:00:19Z)
• X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding [29.479188501343412]
  We introduce X-Stream, the first benchmark dedicated to multi-stream streaming understanding.<n>Comprising 4,220 rigorously curated QA pairs across 932 videos, X-Stream evaluates 11 subtasks across multi-window, multi-view, and multi-device scenarios.
  arXiv  Detail & Related papers  (2026-06-01T16:52:11Z)
• A Survey on Diffusion Language Models [30.00199970146068]
  Diffusion Language Models (DLMs) are an alternative to the dominant autoregressive (AR) paradigm.<n>DLMs possess inherent advantages in reducing inference latency and capturing bidirectional context.<n>Recent advancements have allowed DLMs to show performance comparable to their autoregressive counterparts.
  arXiv  Detail & Related papers  (2025-08-14T17:47:22Z)
• Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward [77.34936657745578]
  We propose Perception-R1, which introduces a novel visual perception reward that explicitly encourages MLLMs to perceive the visual content accurately.<n>We show that Perception-R1 achieves state-of-the-art performance on most benchmarks using only 1,442 training data.
  arXiv  Detail & Related papers  (2025-06-08T16:48:42Z)
• Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency [56.475612147721264]
  We propose a dual-reward formulation that supervises both semantic and temporal reasoning through discrete and continuous reward signals.<n>We evaluate our approach across eight representative video understanding tasks, including VideoQA, Temporal Video Grounding, and Grounded VideoQA.<n>Results underscore the importance of reward design and data selection in advancing reasoning-centric video understanding with MLLMs.
  arXiv  Detail & Related papers  (2025-06-02T17:28:26Z)
• ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning [68.76048244253582]
  We introduce ViaRL, the first framework to leverage rule-based reinforcement learning (RL) for optimizing frame selection in video understanding.<n>ViaRL utilizes the answer accuracy of a downstream model as a reward signal to train a frame selector through trial-and-error.<n>ViaRL consistently delivers superior temporal grounding performance and robust generalization across diverse video understanding tasks.
  arXiv  Detail & Related papers  (2025-05-21T12:29:40Z)
• M$^2$IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineering [21.75002972755496]
  Multimodal in-context learning (ICL) equips Large Vision-language Models (LVLMs) with the ability to adapt to new tasks via multiple user-provided demonstrations.<n>However, its effectiveness is constrained by the token-intensive nature of multimodal inputs and the complexity of cross-modal few-shot reasoning.<n>We propose textbfM$2$IV, a novel representation engineering approach that replaces explicit token-level demonstrations with a set of learnable Multimodal In-context Vectors.
  arXiv  Detail & Related papers  (2025-04-06T22:02:21Z)
• Subtask-Aware Visual Reward Learning from Segmented Demonstrations [97.80917991633248]
  This paper introduces REDS: REward learning from Demonstration with Demonstrations, a novel reward learning framework.<n>We train a dense reward function conditioned on video segments and their corresponding subtasks to ensure alignment with ground-truth reward signals.<n>Our experiments show that REDS significantly outperforms baseline methods on complex robotic manipulation tasks in Meta-World.
  arXiv  Detail & Related papers  (2025-02-28T01:25:37Z)
• ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval [28.13183873658186]
  E-commerce is increasingly multimedia-enriched, with products exhibited in a broad-domain manner as images, short videos, or live stream promotions.<n>Due to large intra-product variance and high inter-product similarity in the broad-domain scenario, a visual-only representation is inadequate.<n>We propose ASR-enhanced Multimodal Product Representation Learning (AMPere)
  arXiv  Detail & Related papers  (2024-08-06T06:24:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.