Pith. sign in

REVIEW 6 cited by

Temporal Reasoning Transfer from Text to Video

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.06166 v1 pith:LXNJCFI7 submitted 2024-10-08 cs.CV cs.CL

classification cs.CVcs.CL
keywords temporalvideoreasoningaccuracyperformancetexttextualachieves
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Video Large Language Models (Video LLMs) have shown promising capabilities in video comprehension, yet they struggle with tracking temporal changes and reasoning about temporal relationships. While previous research attributed this limitation to the ineffective temporal encoding of visual inputs, our diagnostic study reveals that video representations contain sufficient information for even small probing classifiers to achieve perfect accuracy. Surprisingly, we find that the key bottleneck in Video LLMs' temporal reasoning capability stems from the underlying LLM's inherent difficulty with temporal concepts, as evidenced by poor performance on textual temporal question-answering tasks. Building on this discovery, we introduce the Textual Temporal reasoning Transfer (T3). T3 synthesizes diverse temporal reasoning tasks in pure text format from existing image-text datasets, addressing the scarcity of video samples with complex temporal scenarios. Remarkably, without using any video data, T3 enhances LongVA-7B's temporal understanding, yielding a 5.3 absolute accuracy improvement on the challenging TempCompass benchmark, which enables our model to outperform ShareGPT4Video-8B trained on 28,000 video samples. Additionally, the enhanced LongVA-7B model achieves competitive performance on comprehensive video benchmarks. For example, it achieves a 49.7 accuracy on the Temporal Reasoning task of Video-MME, surpassing powerful large-scale models such as InternVL-Chat-V1.5-20B and VILA1.5-40B. Further analysis reveals a strong correlation between textual and video temporal task performance, validating the efficacy of transferring temporal reasoning abilities from text to video domains.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    Temporal information in Video-LLMs is encoded well by video-centric encoders but disrupted by standard projectors; time-preserved MLPs plus AoT supervision yield 98.1% accuracy on arrow-of-time and gains on other temp...

  2. Reasoning Resides in Layers: Restoring Temporal Reasoning in Video-Language Models with Layer-Selective Merging

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    MERIT restores temporal reasoning in VLMs via layer-selective self-attention merging guided by a TR-improving objective that penalizes TP degradation.

  3. P-JEPA: Procedural Video Representation Learning via Joint Embedding Predictive Architecture

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    P-JEPA enables long-form procedural video understanding by predicting pooled masked latent vectors in a dense frame-aligned action space, achieving SOTA fine-grained action classification on EgoExo4D with an order of ...

  4. ReMoT: Reinforcement Learning with Motion Contrast Triplets

    cs.CV 2026-02 conditional novelty 6.0 of 10

    Training a 4B vision-language model on rule-generated motion-contrast triplets with GRPO lifts spatio-temporal QA accuracy by about 17 points on the authors' own benchmark and by smaller margins on standard benchmarks.

  5. GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking

    cs.CV 2026-02 unverdicted novelty 6.0 of 10

    GraphThinker reduces temporal hallucinations in video reasoning by constructing event-based scene graphs and applying visual attention rewards in reinforcement finetuning.

  6. The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

    cs.CL 2026-06 unverdicted novelty 4.0 of 10

    A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.

Pith tools