REVIEW 42 cited by
StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
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
StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
read the original abstract
The rapid development of Multimodal Large Language Models (MLLMs) has expanded their capabilities from image comprehension to video understanding. However, most of these MLLMs focus primarily on offline video comprehension, necessitating extensive processing of all video frames before any queries can be made. This presents a significant gap compared to the human ability to watch, listen, think, and respond to streaming inputs in real time, highlighting the limitations of current MLLMs. In this paper, we introduce StreamingBench, the first comprehensive benchmark designed to evaluate the streaming video understanding capabilities of MLLMs. StreamingBench assesses three core aspects of streaming video understanding: (1) real-time visual understanding, (2) omni-source understanding, and (3) contextual understanding. The benchmark consists of 18 tasks, featuring 900 videos and 4,500 human-curated QA pairs. Each video features five questions presented at different time points to simulate a continuous streaming scenario. We conduct experiments on StreamingBench with 13 open-source and proprietary MLLMs and find that even the most advanced proprietary MLLMs like Gemini 1.5 Pro and GPT-4o perform significantly below human-level streaming video understanding capabilities. We hope our work can facilitate further advancements for MLLMs, empowering them to approach human-level video comprehension and interaction in more realistic scenarios.
Forward citations
Cited by 42 Pith papers
-
AdaThinkV: Adaptive Thinking for Token-Efficient Video Reasoning
A video reasoning model learns per question whether to reason aloud or answer directly, improving accuracy by about 3 points over the best adaptive baseline while using about 23% fewer output tokens.
-
VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance
VIABench provides 761 long-form egocentric videos from blind individuals with 14,526 annotations across three assistance tasks, and shows current multimodal LLMs achieve best overall scores below 30.
-
EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding
EgoSAT is the first benchmark unifying retrospective, online, and prospective reasoning tasks in egocentric streaming video to evaluate VLMs, revealing struggles with temporal modeling and mis-calibration.
-
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.
-
EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision
Egostream introduces a diagnostic benchmark that expands 2,250 questions into 8,528 recall-conditioned evaluations to measure streaming episodic memory performance across detail, spatial, temporal, event, social, caus...
-
An Efficient Streaming Video Understanding Framework with Agentic Control
R3-Streaming uses cascaded control with age-aware memory forgetting and TB-GRPO reinforcement learning to reach SOTA scores of 57.92 on OVO-Bench and 76.36 on StreamingBench with 95-96% fewer visual tokens.
-
Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction
Omni-DuplexEval creates a new benchmark and LLM-as-a-Judge framework for real-time duplex omni-modal interaction, revealing that current models score below 40% overall and struggle especially with proactive responses.
-
Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding
SAVEMem improves streaming video understanding scores by adding semantic awareness to memory compression and query-adaptive retrieval without any model training.
-
Don't Pause! Every prediction matters in a streaming video
SPOT-Bench tests real-time streaming video perception with timeliness metrics, exposing limitations in current models and introducing AsynKV as an improved baseline.
-
OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning
OASIS organizes streaming video into hierarchical events and retrieves memory on-demand via intent-driven refinement to improve long-horizon accuracy and compositional reasoning with bounded token costs.
-
Online Reasoning Video Object Segmentation
The work introduces the ORVOS task, the ORVOSB benchmark with causal annotations across 210 videos, and a baseline using updated prompts plus a temporal token reservoir.
-
VSAS-Bench: Real-Time Evaluation of Visual Streaming Assistant Models
VSAS-Bench offers temporally dense annotations and synchronous/asynchronous protocols to evaluate streaming VLMs on timeliness, consistency, accuracy, and latency trade-offs, showing that adapted conventional VLMs can...
-
StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
StreamGaze is a new benchmark and QA generation pipeline that measures how well MLLMs leverage gaze trajectories for temporal reasoning and proactive intention prediction in streaming egocentric videos.
-
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.
-
Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos
EgoMemo uses multi-scale temporal summaries, a knowledge graph, and visual archives to decide whether and when to intervene proactively on continuous egocentric video, setting baselines on the new EgoServe benchmark o...
-
ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding
A training-free memory framework that anchors streaming video memory to latent objects discovered from frozen Video-LLM features, improving streaming QA accuracy while cutting memory and latency.
-
ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding
Training-free latent-object memory anchors let frozen Video-LLMs retain object histories under a tight token budget and improve streaming and long-video QA.
-
QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding
QSVideo reformulates questions into structured queries, ranks frames by object-action-location relevance plus diversity, and applies temporal strategies to boost VLM accuracy under tight frame budgets.
-
GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video
Current MLLMs can deliver procedural instructions in streaming video but systematically fail at real-time error detection and corrective coaching on the new GuideMe benchmark.
-
MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understanding
MedStreamBench integrates 22 medical datasets into 5,419 QA instances across retrospective, present, future, and proactive temporal settings to evaluate streaming and proactive medical video understanding.
-
ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory
ProtoKV maintains a fixed-capacity summary state for far history in streaming video, improving accuracy by up to 12.5 points in long-delay query scenarios compared to token-retention methods.
-
LiveServe: Interaction-Aware Serving for Real-Time Omni-Modal LLMs
LiveServe exposes audio playback and barge-in signals to the scheduler and KV manager, lowering P90 audio TTFP by 1.55x on average and raising completed-request throughput by 1.15x on two Omni-LMs.
-
Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?
Introduces Ego-MC-Bench benchmark and Ego-CoMist synthetic dataset showing that fine-tuning video LLMs on proactive mistake corrections improves performance especially for smaller models.
-
Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding
LyraV uses FDTC and SToP for per-frame incremental decoding to reach 98.29% video synchrony at 3.89 FPS while preserving general understanding.
-
MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention
MOSS-Video-Preview introduces a cross-attention architecture and synthesized real-time QA data to enable continuous perception, answer revision, and faster inference in video-language models compared to decoder-only designs.
-
StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
StreamOV proposes evidence-guided long-short term memory and a hidden-state-driven trigger for efficient online audio-visual reasoning in streaming videos, along with the SOVBench benchmark for multi-turn evaluation.
-
An Efficient Streaming Video Understanding Framework with Agentic Control
R3-Streaming uses cascaded control, age-aware memory forgetting, and TB-GRPO reinforcement learning to reach SOTA scores on streaming video benchmarks while cutting visual token usage by 95-96%.
-
Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction
Omni-DuplexEval provides a new benchmark and automatic evaluation method for real-time duplex omni-modal interaction, showing state-of-the-art models reach only 39.6% overall and 20% on proactive reminders.
-
Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding
Response-G1 uses query-guided scene graphs, memory retrieval, and augmented prompting to improve when Video-LLMs decide to respond during streaming videos.
-
SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance
Streaming multi-point counting on 406 videos with three trajectory metrics reveals large human-model gaps in spatial-temporal state maintenance, worst on periodic events.
-
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously
A 7B video model that generates intermediate text thoughts during playback, before the query arrives, improves streaming-video QA accuracy while keeping query-time latency near real-time.
-
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.
-
Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
Codec-guided sparse patch selection plus a lightweight speak/silent gate yields a 4B streaming VLM that is competitive on static tasks, stronger on video/spatial benchmarks, and much cheaper at inference.
-
MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering
MuKV adds multi-grained KV cache compression at patch-frame-segment levels plus semi-hierarchical retrieval to raise accuracy and cut memory in long video question-answering.
-
Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding
Response-G1 uses query-guided scene graph generation, memory retrieval, and retrieval-augmented prompting to improve proactive response timing in streaming video understanding.
-
Decouple and Cache: KV Cache Construction for Streaming Video Understanding
DSCache decouples cumulative past and instant KV caches with position-agnostic encoding to adapt offline VideoVLLMs to streaming video, delivering 2.5% average accuracy gains on QA benchmarks.
-
LiveVLN: Breaking the Stop-and-Go Loop in Vision-Language Navigation
LiveVLN enables smoother vision-language navigation by overlapping action execution with ongoing observation processing, preserving benchmark scores while cutting real-world waiting time by up to 77.7 percent.
-
Existence of small semi-vortex solutions for the cubic nonlinear Schr\"{o}dinger system with Rashba type Spin-Orbit coupling on $\mathbb{R}^2$
Existence of small semi-vortex solutions for the Rashba SOC cubic NLS system on R^2 is proved via energy minimization under small mass constraint.
-
Existence of small semi-vortex solutions for the cubic nonlinear Schr\"{o}dinger system with Rashba type Spin-Orbit coupling on $\mathbb{R}^2$
Small semi-vortex and ground-state solutions of the cubic NLS system with Rashba SOC on R² exist as energy minimizers under small mass, via concentration-compactness.
-
Seed1.8 Model Card: Towards Generalized Real-World Agency
Seed1.8 is a new foundation model that adds unified agentic capabilities for search, code execution, and GUI interaction to existing LLM and vision strengths.
-
Seed1.5-VL Technical Report
Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.