SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
read the original abstract
We propose SlowFast-LLaVA (or SF-LLaVA for short), a training-free video large language model (LLM) that can jointly capture detailed spatial semantics and long-range temporal context without exceeding the token budget of commonly used LLMs. This is realized by using a two-stream SlowFast design of inputs for Video LLMs to aggregate features from sampled frames in an effective way. Specifically, the Slow pathway extracts features at a low frame rate while keeping as much spatial detail as possible (e.g., with 12x24 tokens), and the Fast pathway operates on a high frame rate but uses a larger spatial pooling stride (e.g., downsampling 6x) to focus on the motion cues. As a result, this design allows us to adequately capture both spatial and temporal features that are beneficial for detailed video understanding. Experimental results show that SF-LLaVA outperforms existing training-free methods on a wide range of video tasks. On some benchmarks, it achieves comparable or even better performance compared to state-of-the-art Video LLMs that are fine-tuned on video datasets. Code has been made available at: https://github.com/apple/ml-slowfast-llava.
This paper has not been read by Pith yet.
Forward citations
Cited by 19 Pith papers
-
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Molmo2 delivers state-of-the-art open-weight video VLMs with new grounding datasets and training methods that outperform prior open models and match or exceed some proprietary ones on pointing and tracking tasks.
-
TrajTok: Learning Trajectory Tokens enables better Video Understanding
TrajTok learns adaptive trajectory tokens for videos through a unified end-to-end segmenter, improving understanding performance and efficiency over patch-based or external-pipeline tokenizers.
-
WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
WorldSense provides the first benchmark requiring synergistic audio-video-text understanding on 1,662 real-world videos and 3,172 QA pairs, where the best current multimodal LLM reaches only 65.1% accuracy.
-
Q-Fold: Query-Aware Focus-Context Spatio-Temporal Folding for Long Video Understanding
Q-Fold is a query-aware spatio-temporal folding technique that constructs heterogeneous focus-context inputs from long videos to improve Video-MLLM performance under fixed visual budgets.
-
MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering
MemoryCard organizes long videos into self-contained topic-aware Memory Cards that improve long-video QA accuracy by up to 21.8% relative under fixed visual-token budgets.
-
V-LynX: Token Interface Alignment for Video+X LLMs
V-LynX integrates novel modalities into frozen Video LLMs by aligning to an internalized continuous token manifold using unpaired unimodal data and attention/statistical matching.
-
WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization
WindowQuant performs window-adaptive mixed-precision KV cache quantization guided by similarity to the text prompt, with reordering to enable efficient inference in VLMs.
-
One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
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 ...
-
LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval
LiveVLM introduces VSB and PaR to compress and retrieve KV cache in streaming video LLMs, enabling LLaVA-OneVision to reach SOTA accuracy among training-free query-agnostic and training-based online models.
-
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
LongVU adaptively compresses long video tokens using DINOv2-based frame deduplication, text-guided cross-modal selection, and temporal spatial reduction to improve video-language understanding in MLLMs with minimal de...
-
LLaVA-Video: Video Instruction Tuning With Synthetic Data
LLaVA-Video-178K is a new synthetic video instruction dataset that, when combined with existing data to train LLaVA-Video, produces strong results on video understanding benchmarks.
-
ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference
ViCoStream is a new coordinated pipeline framework for streaming VideoLLMs that achieves 134 FPS video throughput and less than 50 ms TTFT on A100 while keeping accuracy near full-history baselines.
-
Linear Scaling Video VLMs for Long Video Understanding
StateKV is an inference-time technique that replaces quadratic self-attention prefill in video VLMs with a fixed-capacity importance-based recurrent state, keeping accuracy near full attention on long-video benchmarks...
-
VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer
VidPrism introduces a heterogeneous temporal MoE with content-aware multi-rate sampling and bidirectional fusion for image-to-video transfer, claiming SOTA results on video benchmarks.
-
EgoSelf: From Memory to Personalized Egocentric Assistant
EgoSelf uses graph-based memory of user interactions to derive personalized profiles and predict future behaviors for egocentric assistants.
-
MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models
MASS adds spatiotemporal motion signals and 3D grounding to VLMs and releases MASS-Bench, yielding physics-reasoning performance within 2% of Gemini-2.5-Flash after reinforcement fine-tuning.
-
Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
Video Parallel Scaling improves VideoLLM performance by aggregating outputs from parallel inferences on complementary disjoint frame subsets, effectively contracting the Chinchilla scaling law via uncorrelated visual ...
-
NVILA: Efficient Frontier Visual Language Models
NVILA improves on VILA with a scale-then-compress visual token strategy and full-lifecycle efficiency optimizations, matching or exceeding leading VLMs on image and video benchmarks while reducing training cost 1.9-5....
-
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.