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.
hub Mixed citations
Videochat-r1
Mixed citation behavior. Most common role is background (62%).
22
Pith papers citing it
Background
62% of classified citations
hub tools
citation-role summary
background 5
baseline 3
citation-polarity summary
representative citing papers
Introduces OMTG benchmark with C-Acc and EtF1 metrics, a 56k dataset, and caption/temporal rewards, reaching 43.65% EtF1 SOTA on the new bench.
Moment-Video benchmark shows top video MLLM achieves only 39.6% accuracy on momentary visual event tasks, with most open-source models below 25%.
VideoOdyssey is a new benchmark featuring ultra-long videos (avg. 109 min) across 11 domains with multi-level continuous certificates (avg. 16 min for visual, 12.8 min for audio-visual) to diagnose MLLM limitations in continuous reasoning and omni-modal perception.
GRASP is a large-scale dataset and benchmark for social reasoning grounded in gaze and gesture events in multi-person videos, with Social Grounding Reward (SGR) proposed to improve model performance on GRASP-Bench.
A proposer-solver agent pair achieves supervised-level video temporal grounding and fine-grained captioning from 2.5K unlabeled videos via self-reinforcing evolution.
TOC-Bench is a new diagnostic benchmark that reveals major weaknesses in temporal object consistency for Video-LLMs, including event counting, ordering, identity reasoning, and hallucination avoidance.
LMMs perceive videos but underexploit visual content for causal reasoning due to textual shortcuts; ProCauEval diagnoses this and ADPO training reduces reliance on priors.
VisReflect generates continuous latent visual reflections to emphasize relevant visual features and guide attention in LVLMs, yielding 4.1% gains on image benchmarks and 1.8% on video benchmarks with 44% less inference time than zooming methods.
CineCap combines structured reasoning and RL rewards to outperform baselines on cinematographic video captioning using a new 472-pair benchmark.
CHAI framework pairs AI pre-captions with expert human critiques to produce precise video descriptions, enabling open models to outperform closed ones like Gemini-3.1-Pro and improve fine-grained control in video generation models.
Video-MME-v2 is a new benchmark that applies progressive visual-to-reasoning levels and non-linear group scoring to expose gaps in video MLLM capabilities.
RLER trains video-reasoning models with three task-driven RL rewards for evidence production and elects the best answer from a few candidates via evidence consistency scoring, yielding 6.3% average gains on eight benchmarks.
G2F-RAG converts retrieved knowledge subgraphs into a single visual reasoning frame appended to videos, enabling training-free and interpretable improvements for LMM-based video reasoning on knowledge-intensive tasks.
Skyra is an MLLM that detects AI-generated videos by identifying and reasoning over grounded visual artifacts, supported by a new annotated dataset and benchmark.
REVISOR adds multimodal visual-text reflection and a Dual Attribution Decoupled Reward to improve long-form video reasoning in MLLMs without extra supervised fine-tuning.
A survey of test-time scaling for multimodal foundation models that introduces a three-way taxonomy of sampling, feedback, and search approaches along with applications and benchmarks.
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.
TempR1 applies temporal-aware multi-task RL using GRPO and three types of localization rewards to achieve SOTA temporal understanding in MLLMs with synergistic gains from joint optimization.
This is a survey that frames video MLLM research via a human-view formulation of perceptual representations, memory states, reasoning traces, and predictions, then reviews methods, datasets, benchmarks, and open problems.
Empirical study on ImplicitQA benchmark finds video QA is perception-bound, with reasoning augmentations neutral or harmful and low-level perception categories hardest.