The paper introduces VT-Contrast, a representation-level temporal counterfactual objective designed to improve temporal understanding in Video Language Models (VideoLMs). By supervising late-layer last-frame video tokens and contrasting order-preserving views with reordered counterfactuals graded by Kendall tau distance, VT-Contrast addresses the mismatch between ordered video input and text-based supervision. The method requires no architectural changes, is compatible with various VideoLM training tasks, and demonstrates improved performance on temporal understanding benchmarks.
arXiv:2505.01583v2 Announce Type: replace Abstract: Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models (VLM...
Kairos is a new video dataset designed for fine-grained video-language modeling, featuring long-duration videos from ten minutes to half an hour. Each video is annotated with time-resolved labels that capture ongoing actions, entity appearances, attributes, interactions, and evolving contextual cues throughout the timeline. The dataset supports fine-grained evaluation, long-range modeling, reasoning, instruction data construction, representation learning, and video generation.
TimeBlind is a diagnostic benchmark designed to evaluate fine‑grained spatio‑temporal compositionality in video large language models (LLMs). It categorizes temporal understanding into three levels—atomic event recognition, event property characterization, and reasoning about event interdependencies—and uses a minimal‑pairs paradigm where video pairs share identical static content but differ only in temporal structure. Across 20 state‑of‑the‑art MLLMs tested on 600 curated instances, the best model achieved only 48.2% instance accuracy, far below human performance of 98.2%, highlighting a reliance on static visual shortcuts rather than true temporal reasoning.
The paper introduces Temporal Activation Injection (TAI), a post‑processing technique that reinforces temporal representations in Video Large Language Models (VideoLLMs) at inference time. By measuring the temporal divergence vector τ_l— the layer‑wise difference caused by reversing video frame order— the authors find that temporal information peaks at intermediate layers and fades toward the output. TAI injects the peak divergence back into later layers, improving temporal reasoning on three VideoLLMs across four benchmarks without affecting non‑temporal performance.
The paper introduces STITCH, a training‑free method that partitions videos into semantically meaningful temporal chunks using a frozen video‑text backbone. By detecting changes in the embedding sequence of short video windows, STITCH produces reusable temporal abstractions that can be applied to multiple tasks such as event boundary detection, language‑based moment retrieval, and frame selection for vision‑language models. Experiments show that STITCH performs competitively with specialized methods while requiring no task‑specific training, especially when processing is limited to a few frames or tokens.
The paper introduces Temporal Specification Guidance (TSG), a training‑free inference framework that uses Temporal Logic specifications to guide text‑to‑video generation. TSG evaluates visual concept traces with differentiable quantitative semantics and adjusts the denoising direction via gradient‑derived attention biases, eliminating the need for external classifiers or backpropagation through the transformer. Experiments on 220 prompts across 11 temporal constraint categories show that TSG improves specification satisfaction by 9.5–20 percentage points over classifier‑free guidance with minimal memory overhead.
The paper introduces structured video prompting, a training‑free inference‑time technique that augments input videos with lightweight spatial and temporal structure to provide explicit anchors for evidence organization. By applying this method to two video benchmarks and two open video‑language models, the authors demonstrate performance improvements across several tasks, with gains varying by model and task. The study suggests that failures in video‑language models stem not only from reasoning capacity but also from how video evidence is presented during inference.
Recent advancements in Vision-Language Models (VLMs) have significantly enhanced their ability to interpret complex visual semantics, yet their capacity for chronological reasoning remains under-explored. In this paper, we introduce a novel benchmark specifically designed to evaluate how VLMs perceive and reason about chronological information within and across images.
arXiv:2609.34581v2 Announce Type: replace Abstract: Temporal video grounding is a key capability of advanced Multimodal Large Language Models (MLLMs) for the thorough understanding of video events, w...
arXiv:2606. 05702v1 Announce Type: new Abstract: Recent advancements in Vision-Language Models (VLMs) have significantly enhanced their ability to interpret complex visual semantics, yet their capacity for chronological reasoning remains under-explored.
Event-Causal RAG (EC‑RAG) is a lightweight retrieval‑augmented framework designed for reasoning over ultra‑long and streaming videos. It segments video streams into semantically complete events using a dual visual‑audio sentinel mechanism, representing each event as a State‑Event‑State (SES) structure that captures pre‑event, event, and post‑event states. During question answering, bidirectional graph retrieval accesses relevant predecessor and successor events from a dual vector‑graph memory, and answers are generated using both this structured memory and the corresponding video evidence. The authors also introduce ECV‑1H, an hour‑scale long‑video QA benchmark with over 150 hours of untrimmed video and 1,251 human‑annotated QA pairs, where EC‑RAG achieves significant accuracy gains across multiple video foundation models while maintaining efficient streaming memory usage on a single RTX 5090 GPU.
arXiv:2605.29858v3 Announce Type: replace Abstract: Temporal action localization (TAL) requires recognizing the target event and localizing its start and end times precisely in untrimmed videos. Rece...