The paper proposes a unified framework that decouples long-video reasoning into semantic and visual evidence, significantly improving performance on the HD-EPIC VQA Challenge.

The paper introduces Moment-Video, a new benchmark that diagnoses the ability of video MLLMs to understand brief, critical visual events, revealing that current models struggle significantly with temp…

LongLive-RAG proposes a novel Retrieval-Augmented Generation (RAG) framework to stabilize and improve the quality of long-horizon video generation by treating the entire generated history as a searcha…

The paper introduces and analyzes 'temporal framing,' defining it as the persuasive use of time-related language in news, and demonstrates that this framing can be effectively detected using supervise…

LongTraceRL addresses long-context reasoning challenges by generating highly challenging training data and introducing a fine-grained rubric reward, significantly improving evidence-grounded reasoning…

This paper demonstrates that fine-tuning small language models (SLMs) on a synthetic, solution-rich Windows event log dataset allows them to outperform larger LLMs in identifying issues and providing…

The paper proposes a training-free framework, Visual Representation-Guided Video-LLM Reasoning, to perform composed video retrieval by using visual examples and text instructions, achieving strong per…

The paper systematically evaluates concept-based explainability in MLLMs, finding that forcing models to generate formal explanations degrades predictive accuracy, suggesting that explaining is genuin…

SmartDirector is a novel framework that significantly improves cinematic video generation by using multiple keyframes to provide precise control over narrative structure and temporal pacing.

The paper proposes a market-feedback adaptive retrieval system for frozen LLMs in financial RAG, significantly improving event-impact prediction by learning which evidence sources to prioritize.

The paper proposes BitTP, a lightweight bitlinear architecture that quantizes LLM-based trajectory predictors to 1.58-bit weights while keeping activations full-precision, enabling high-performance de…

This paper addresses the challenge of detecting and explaining AI-manipulated segments within long, untrimmed videos by proposing a new benchmark and a coarse-to-fine forensic detection framework.

SHARP proposes a novel sleep-based hierarchical replay framework to efficiently learn long-range non-stationary temporal patterns in streaming data, achieving improved context retention and predictive…

MemGuard introduces a type-aware memory framework to prevent heterogeneous memory contamination in long-term memory-augmented LLMs, significantly improving memory reliability and efficiency.

The paper introduces a novel paradigm where a fine-tuned LLM acts as an ancillary predictor to forecast likely advertisers, significantly improving ad recommendation systems by augmenting candidate ge…