Dispute mediation is essential for maintaining social harmony and resilience, yet developing skilled mediators is costly and time-consuming. Existing LLM-based mediation research remains limited by unrealistic task formulations, low-fidelity datasets, and coarse evaluation metrics that obscure turn-by-turn dynamics. To address these gaps, we introduce ProMediConv, a novel benchmarking framework that models mediation as a proactive, multi-stage, and party-aware dialogue process incorporating 11 mediation strategies and four party behavior pattern (BP) states. Using 972 complete real-world cases, we construct a high-fidelity mediation dataset with utterance-level annotations of strategies and BP states. Furthermore, to better assess agent impact, we propose MAD (Mean Attribute Difference), a fine-grained metric that captures BP shifts throughout the dialogue. Leveraging this framework, we establish a comprehensive benchmark by evaluating diverse models alongside our tailored baseline ProMediAgent. Extensive empirical analyses reveal critical behavioral phenomena and underscore the persistent challenges current models face in dynamic, multi-party mediation. Ultimately, ProMediConv provides a rigorous foundation and a vital quantitative standard for advancing AI-assisted conflict resolution. Our dataset and codebase are accessible at https://github.com/ZsWei66/ProMediConv_repo.

Video Large Language Models (VideoLLMs) struggle with the heavy computational cost of long or high-resolution videos due to massive visual token counts and the quadratic complexity of attention. Prior pruning approaches mainly rely on token importance or similarity, while largely overlooking video dynamics and the fact that different scenes exhibit different redundancy patterns. We introduce MoPrune, a training-free, scene-guided and motion-centric token pruning framework for accelerating VideoLLMs. MoPrune first segments videos into semantically coherent scenes to preserve temporal and motion consistency. Within each scene, it determines frame retention rates from intra-scene frame uniqueness. Finally, at the token level, MoPrune retains visually distinctive tokens and motion-salient tokens via a unified score, preserving both informative static details and dynamic regions. Extensive experiments across multiple VideoLLMs and public benchmarks demonstrate MoPrune’s superior efficiency–performance trade-offs. On LLaVA-OneVision, retaining 25% of visual tokens matches or slightly improves the dense baseline, and retaining 15% tokens preserves 99% of the original performance. MoPrune is fully compatible with hardware-efficient techniques such as Flash Attention.

Weakly-supervised temporal action localization (WS-TAL) remains challenging due to the severe temporal ambiguity inherent in video-level supervision. Existing methods often overfit to highly discriminative snippets, struggling to capture the complete action extent. In this paper, we reconceptualize actions not as isolated events, but as multi-stage action evolutions. To alleviate temporal ambiguity, we propose a novel framework driven by Linguistic Temporal Knowledge Transfer (LTKT) Network, comprising three cohesive modules. First, Temporal Stage Grounding (TSG) leverages explicitly deconstructed LLM descriptions as cross-modal priors, guiding unconstrained visual snippets to anchor their specific evolutionary stages. Second, Temporal Transition Gating (TTG) enforces forward causality on the timeline. By mandating that an execution stage is flanked by historical preparation and future completion, TTG strictly filters static noise to yield refined temporal action scores. Finally, Linguistic Knowledge Transfer (LKT) integrates knowledge distillation and contrastive learning to embed this structural knowledge into the visual backbone. Extensive experiments on THUMOS14, ActivityNet1.2 and ActivityNet1.3 demonstrate that our method achieves state-of-the-art performance.