TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding

Yibo Ma; Qianqian Zhang; Peng Liu; Tiancheng Zhao

Home/Archive/arXiv

arXiv · 2609.30670

TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding

Yibo Ma·Qianqian Zhang·Peng Liu·Tiancheng Zhao

View original source ↗Read source document ↗Export metadata ↓

Abstract

Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluations often report task scores without specifying when evidence becomes valid, how visual history is maintained, or how responses are triggered. As a result, similar scores may correspond to different workloads, failure modes, and operational behavior. We introduce TRACE (Temporal Audit and Condition-aware Evaluation), a condition-aware benchmark and evaluation framework that makes these factors explicit. TRACE combines temporally audited visual tasks with evidence timing and instruction-dependent trigger annotations, a unified causal Core--Adapter protocol that controls information availability while recording actual history processing and response events, and multidimensional reporting of answer quality, timeliness, response-selection behavior, workload, completion, and reliability. On 1,240 records from 517 videos, we evaluate eight publicly available models or systems in eight configurations. We find that nearly identical QA accuracy can mask substantial differences in completion, answer validity, and generation workload, while proactive performance separates into response quality, response delay, false alarms (responses emitted while no target window is currently valid and a later one remains), and missed target windows. These results show that streaming-video performance should be interpreted as execution-conditioned system behavior rather than a single score. Our benchmark and code can be accessed at \href{https://github.com/om-ai-lab/trace-bench}{https://github.com/om-ai-lab/trace-bench}.

Explore related subjects

cs.CL cs.CV

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Yibo Ma, Qianqian Zhang, Peng Liu, Tiancheng Zhao. 2026-09-25. TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding. https://arxiv.org/abs/2609.30670

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

MedHal: a Synthetic Dataset for Medical Hallucination Detection

Hallucination, the generation of non factual content by AI systems, poses serious risks in medical contexts, where errors can directly affect patient outcomes. We present MedHal, a large-scale dataset specifically designed to assess capabilities and train models on the task of hallucination detection in medical texts. Current hallucination detection methods face significant limitations when applied to specialized domains like medicine, where they can have disastrous consequences. MedHal addresses this issue by incorporating diverse medical text sources and tasks covering both intrinsic and extrinsic hallucinations, and by providing a substantial volume of data samples suitable for training medical hallucination detection models. We demonstrate MedHal's utility by training and evaluating a baseline medical hallucination detection model, showing improvements over general-purpose hallucination detection approaches. This resource enables more efficient evaluation and training of medical text generation systems while reducing reliance on costly expert review, potentially accelerating the development of medical AI research.

cs.CL↗

arXiv2026

Affective Flow Language Model for Emotional Support Conversation

Large language models (LLMs) have advanced emotional support conversation, but existing alignment methods rely mainly on sparse preferences at the response level or outcomes at the dialogue level, providing limited supervision for sequential strategy decisions in multi-turn interactions. This raises a key question: how can detailed process signals be derived from overall dialogue outcomes to guide the gradual adaptation of support strategies? We propose the Affective Flow Language Model (AFlow), which models multi-turn emotional support as an affective utility flow evolving along dialogue trajectories. AFlow searches diverse support trajectories and estimates the utility of intermediate dialogue states and candidate strategies. It further introduces Affective Flow Preference Optimization (AFPO), which uses a flow-balance objective defined over dialogue subpaths to propagate downstream preference signals to intermediate states and learn strategy transitions consistent with support outcomes over the full dialogue. AFlow introduces flow-balance learning into multi-turn affective interaction, providing a process-based approach to dynamic affect modeling and continuous strategy optimization. Experiments on ExTES and ESConv show consistent improvements in strategy alignment, response diversity, and generation quality across different model environments and evaluation settings. Our code is available at https://github.com/chz2025/AffectiveFlow.

cs.CL↗

arXiv2026

Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR

Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR architectures connect a speech encoder to a large language model via a projection module, enabling adaptation with text-only data. However, this introduces a modality gap, as the LLM is not exposed to the noisy representations produced by the speech projector. We investigate whether small amounts of speech can mitigate this mismatch. We compare three strategies: text-only adaptation, paired speech-text adaptation, and mixed batching (MB), which combines both. Experiments in in-domain and out-of-domain settings show that even limited speech consistently improves performance. Notably, MB using only 10% of the target-domain (less than 4 hours) speech achieves word error rates comparable to, or better than, conventional ASR fine-tuning with the full dataset, indicating that small amounts of speech provide a strong modality-alignment signal.

cs.CL↗