A proposer-solver agent pair achieves supervised-level video temporal grounding and fine-grained captioning from 2.5K unlabeled videos via self-reinforcing evolution.
hub
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
abstract
The Large Vision-Language Model (LVLM) has enhanced the performance of various downstream tasks in visual-language understanding. Most existing approaches encode images and videos into separate feature spaces, which are then fed as inputs to large language models. However, due to the lack of unified tokenization for images and videos, namely misalignment before projection, it becomes challenging for a Large Language Model (LLM) to learn multi-modal interactions from several poor projection layers. In this work, we unify visual representation into the language feature space to advance the foundational LLM towards a unified LVLM. As a result, we establish a simple but robust LVLM baseline, Video-LLaVA, which learns from a mixed dataset of images and videos, mutually enhancing each other. Video-LLaVA achieves superior performances on a broad range of 9 image benchmarks across 5 image question-answering datasets and 4 image benchmark toolkits. Additionally, our Video-LLaVA also outperforms Video-ChatGPT by 5.8%, 9.9%, 18.6%, and 10.1% on MSRVTT, MSVD, TGIF, and ActivityNet, respectively. Notably, extensive experiments demonstrate that Video-LLaVA mutually benefits images and videos within a unified visual representation, outperforming models designed specifically for images or videos. We aim for this work to provide modest insights into the multi-modal inputs for the LLM. Code address: \href{https://github.com/PKU-YuanGroup/Video-LLaVA}
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
polarities
background 2representative citing papers
EyeCue detects driver cognitive distraction by modeling gaze-visual context interactions in egocentric videos and achieves 74.38% accuracy on the new CogDrive dataset, outperforming 11 baselines.
LearnPruner prunes vision tokens to 5.5% of the original count while retaining about 95% of VLM performance and delivering 3.2 times faster inference by fixing attention sink in encoders and using unbiased middle-layer attention in LLMs.
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 robustness and weak spatial performance.
SAri-RFT applies GRPO-based reinforcement fine-tuning to LVLMs on novel two-term and three-term visual semantic arithmetic tasks, reaching SOTA on the new IRPD dataset and Visual7W-Telling.
SVAgent improves long video question answering by constructing storylines via multi-agent collaboration and aligning cross-modal predictions for more robust, human-like reasoning.
MLVU is a new benchmark for long video understanding that uses extended videos across diverse genres and multi-task evaluations, revealing that current MLLMs struggle significantly and degrade sharply with longer durations.
SpaceMind++ adds an explicit voxelized allocentric cognitive map and coordinate-guided fusion to video MLLMs, claiming SOTA on VSI-Bench and improved out-of-distribution generalization on three other 3D benchmarks.
WindowQuant performs window-adaptive mixed-precision KV cache quantization guided by similarity to the text prompt, with reordering to enable efficient inference in VLMs.
ForeSight lets VLMs use low-level visual cues and mask-based visual feedback within an RL loop to reason more accurately, with the 7B model beating same-scale peers and some closed-source SOTA on a new benchmark.
UniCon unifies contrastive alignment across encoders and alignment types using kernels to enable exact closed-form updates instead of stochastic optimization.
XComp reaches extreme video compression (one token per selective frame) via learnable progressive token compression and question-conditioned frame selection, lifting LVBench accuracy from 42.9 percent to 46.2 percent after tuning on 2.5 percent of standard data.
ViLL-E introduces a dynamic embedding mechanism and joint contrastive-generative training for VideoLLMs, delivering up to 7% gains in temporal localization and 4% in video retrieval while enabling new zero-shot capabilities.
CFMS is a coarse-to-fine framework that uses MLLMs to create a multi-perspective knowledge tuple as a reasoning map for symbolic table operations, yielding competitive accuracy on WikiTQ and TabFact.
FESTS uses Spatial Regular Expressions compiled from queries to generate 27k training tuples that raise a 3B-parameter LLM's frame-level F1 on spatio-temporal video reasoning from 48.5% to 87.5%, matching GPT-4.1 while staying far smaller.
ProVCA progressively condenses long videos via segment localization, snippet selection, and keyframe refinement to achieve SOTA zero-shot accuracies on EgoSchema, NExT-QA, and IntentQA with fewer frames.
ImgEdit supplies 1.2 million curated edit pairs and a three-part benchmark that let a VLM-based model outperform prior open-source editors on adherence, quality, and detail preservation.
UniWorld-V1 shows that semantic features from large multimodal models enable unified visual understanding and generation, achieving strong results on perception and manipulation tasks with only 2.7 million training samples.
LLaVA-OneVision is the first single open LMM to simultaneously achieve strong performance in single-image, multi-image, and video scenarios with cross-scenario transfer capabilities.
VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.
VideoLLaMA 2 improves video LLMs via a new STC connector for spatial-temporal dynamics and joint audio training, reaching competitive results on video QA and captioning benchmarks.
This survey reviews the definition, symptoms, evaluation benchmarks, root causes, and mitigation methods for hallucinations in large vision-language models.
citing papers explorer
-
MLVU: Benchmarking Multi-task Long Video Understanding
MLVU is a new benchmark for long video understanding that uses extended videos across diverse genres and multi-task evaluations, revealing that current MLLMs struggle significantly and degrade sharply with longer durations.
-
ImgEdit: A Unified Image Editing Dataset and Benchmark
ImgEdit supplies 1.2 million curated edit pairs and a three-part benchmark that let a VLM-based model outperform prior open-source editors on adherence, quality, and detail preservation.