REVIEW 32 cited by
V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning
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
V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning
read the original abstract
Human processes video reasoning in a sequential spatio-temporal reasoning logic, we first identify the relevant frames ("when") and then analyse the spatial relationships ("where") between key objects, and finally leverage these relationships to draw inferences ("what"). However, can Video Large Language Models (Video-LLMs) also "reason through a sequential spatio-temporal logic" in videos? Existing Video-LLM benchmarks primarily focus on assessing object presence, neglecting relational reasoning. Consequently, it is difficult to measure whether a model truly comprehends object interactions (actions/events) in videos or merely relies on pre-trained "memory" of co-occurrences as biases in generating answers. In this work, we introduce a Video Spatio-Temporal Reasoning (V-STaR) benchmark to address these shortcomings. The key idea is to decompose video understanding into a Reverse Spatio-Temporal Reasoning (RSTR) task that simultaneously evaluates what objects are present, when events occur, and where they are located while capturing the underlying Chain-of-thought (CoT) logic. To support this evaluation, we construct a dataset to elicit the spatial-temporal reasoning process of Video-LLMs. It contains coarse-to-fine CoT questions generated by a semi-automated GPT-4-powered pipeline, embedding explicit reasoning chains to mimic human cognition. Experiments from 14 Video-LLMs on our V-STaR reveal significant gaps between current Video-LLMs and the needs for robust and consistent spatio-temporal reasoning.
Forward citations
Cited by 32 Pith papers
-
PinpointQA: A Dataset and Benchmark for Small Object-Centric Spatial Understanding in Indoor Videos
PinpointQA is the first benchmark dataset for small object-centric spatial understanding in indoor videos, with four tasks showing MLLM capability gaps that improve via supervised fine-tuning.
-
ToG-Bench: Task-Oriented Spatio-Temporal Grounding in Egocentric Videos
ToG-Bench is the first benchmark for task-oriented spatio-temporal video grounding in egocentric videos, with explicit-implicit dual grounding and one-to-many object scenarios across 100 ScanNet clips and 2704 instructions.
-
AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models
AnyGroundBench is a domain-adaptation benchmark for spatio-temporal video grounding across animal, industry, sports, surgery, and public security domains that finds 15 state-of-the-art VLMs fail in zero-shot and ICL settings.
-
Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning
Introduces Video-MME-Logical benchmark for controlled diagnostic evaluation of temporal-logical reasoning in MLLMs via five operations and 25 fine-grained tasks.
-
X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding
X-Stream benchmark shows SOTA MLLMs score ~50% on concurrent multi-stream tasks and lack proactive ability, using a dual-verification pipeline to avoid single-stream bias.
-
X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding
X-Stream benchmark shows state-of-the-art MLLMs achieve only about 50% on multi-stream video tasks and exhibit poor proactive ability.
-
Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models
STEMO-Bench evaluates intermediate spatio-temporal reasoning in video MLLMs via object-centric facts, and STEMO-Track improves consistency by chunk-wise trajectory construction and aggregation.
-
VISD: Enhancing Video Reasoning via Structured Self-Distillation
VISD improves VideoLLM reasoning performance and training efficiency by combining structured multi-dimensional self-distillation feedback with RL via direction-magnitude decoupling, curriculum scheduling, and EMA stab...
-
Grounding Video Reasoning in Physical Signals
A new benchmark converts video clips into shared grounded event records and tests models across physics, semantic, and control prompts under original, shuffled, ablated, and masked conditions, finding selective robust...
-
PinpointQA: A Dataset and Benchmark for Small Object-Centric Spatial Understanding in Indoor Videos
PinpointQA is the first benchmark dataset for small object-centric spatial understanding in indoor videos, with four progressive tasks built from ScanNet data.
-
Reasoning over Video: Evaluating How MLLMs Extract, Integrate, and Reconstruct Spatiotemporal Evidence
VAEX-BENCH shows state-of-the-art MLLMs perform substantially worse on abstractive spatiotemporal reasoning tasks than on matched extractive tasks in video understanding.
-
Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
Video-Holmes benchmark shows top MLLMs achieve at most 45% accuracy on tasks needing integration of multiple clues from suspense films, unlike existing perception-focused tests.
-
CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs
CARE uses exponential moving average competence estimates to progressively shift RL rewards from exploration-oriented long reasoning to efficiency-oriented concise reasoning in video-MLLMs, with batch normalization an...
-
Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
Maestro uses outcome-based RL to train a lightweight policy that orchestrates ensembles of frozen expert models and skills, reporting 70.1% average accuracy across ten multimodal benchmarks and outperforming GPT-5 and...
-
Leveraging Latent Visual Reasoning in Silence
Latent visual reasoning improves multimodal models via training effects even without using latent tokens at inference, enabled by an attention-based RL reward that promotes interaction with text tokens.
-
STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning
STAR combines expert nominal routes with trace-learned recovery transitions in a failure-typed routing matrix, improving multi-agent spatiotemporal reasoning over baselines especially on error-deviating queries.
-
STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning
STAR presents a failure-aware routing framework using a state-conditioned transition policy and an agent routing matrix combining expert routes with learned recoveries from execution traces to improve multi-agent spat...
-
State Beyond Appearance: Diagnosing and Improving State Consistency in Dial-Based Measurement Reading
MLLMs ignore dial state geometry and cluster by appearance, causing inconsistency under variations; TriSCA's state-distance alignment, metadata supervision, and objective alignment improve robustness on clock and gaug...
-
Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models
Position and step penalty plus visual reasoning guidance fix premature answering and weak visual grounding in diffusion MLLMs, delivering up to 7.5% accuracy gains and over 3x speedup.
-
GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking
GraphThinker reduces temporal hallucinations in video reasoning by constructing event-based scene graphs and applying visual attention rewards in reinforcement finetuning.
-
$M^3-Verse$: A "Spot the Difference" Challenge for Large Multimodal Models
A new benchmark tests whether large multimodal models can compare paired 'before and after' videos to detect scene changes, and finds current models perform near random.
-
Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding
DEViL offloads spatial grounding to a detector via a distilled reference-semantic token and temporal consistency regularization, reaching 43.1% m_vIoU at 14.33 FPS on HC-STVG.
-
SPHINX: A Synthetic Environment for Visual Perception and Reasoning
SPHINX generates synthetic visual puzzles for benchmarking LVLMs, where GPT-5 scores 51.1% and RLVR training improves both in-domain and external visual reasoning performance.
-
Video Reasoning without Training
An entropy-guided, inference-time value-cache controller improves video reasoning accuracy and cuts output tokens versus RL-trained baselines.
-
MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding
MUSEG applies timestamp-aware multi-segment grounding with a phased-reward RL recipe to boost temporal grounding and time-sensitive video QA performance in MLLMs.
-
EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs
EgoCoT-Bench provides 3,172 verifiable QA pairs across perception, anticipation, and reasoning tasks on egocentric videos, revealing that many MLLMs give answer-correct but evidence-inconsistent explanations.
-
STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning
STAR is a failure-aware Markovian router that learns recovery transitions from both successful and unsuccessful execution traces to improve multi-agent performance on spatiotemporal benchmarks.
-
VISD: Enhancing Video Reasoning via Structured Self-Distillation
VISD proposes structured self-distillation with a multi-dimensional judge model and direction-magnitude decoupling to improve token-level credit assignment and convergence speed in VideoLLM reasoning training.
-
VISD: Enhancing Video Reasoning via Structured Self-Distillation
VISD adds structured privileged feedback from a judge model and a direction-magnitude decoupling trick to let VideoLLMs learn token-level credit assignment while keeping RL stable, yielding higher accuracy and roughly...
-
VISD: Enhancing Video Reasoning via Structured Self-Distillation
VISD improves VideoLLM reasoning by adding multi-dimensional diagnostic self-distillation and RL decoupling, yielding higher accuracy, better grounding, and nearly 2x faster training convergence.
-
Lost in the Vibrations: Vision Language Models Fail the Dynamic Gauges Test
Vision-language models fail to accurately interpret dynamic analog gauge readings involving needle vibrations and high-frequency movements.
-
LanteRn: Latent Visual Structured Reasoning
A 3B vision-language model trained to emit latent visual thought tokens interleaved with text, then refined by reinforcement learning, outperforms a matched text-only baseline on several visual reasoning benchmarks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.