Pith. sign in

REVIEW 9 cited by

StreamChat: Chatting with Streaming Video

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

arxiv 2412.08646 v2 pith:2DQVLJV2 submitted 2024-12-11 cs.CV

classification cs.CV
keywords streamingvideointeractionstreamchatvisualcapabilitiescontentdecoding
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This paper presents StreamChat, a novel approach that enhances the interaction capabilities of Large Multimodal Models (LMMs) with streaming video content. In streaming interaction scenarios, existing methods rely solely on visual information available at the moment a question is posed, resulting in significant delays as the model remains unaware of subsequent changes in the streaming video. StreamChat addresses this limitation by innovatively updating the visual context at each decoding step, ensuring that the model utilizes up-to-date video content throughout the decoding process. Additionally, we introduce a flexible and efficient crossattention-based architecture to process dynamic streaming inputs while maintaining inference efficiency for streaming interactions. Furthermore, we construct a new dense instruction dataset to facilitate the training of streaming interaction models, complemented by a parallel 3D-RoPE mechanism that encodes the relative temporal information of visual and text tokens. Experimental results demonstrate that StreamChat achieves competitive performance on established image and video benchmarks and exhibits superior capabilities in streaming interaction scenarios compared to state-of-the-art video LMM.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Think in Sets for Streaming Video Token Compression

    cs.CV 2026-08 conditional novelty 7.0 of 10

    NovaCov uses a bounded, recency-weighted historical reference bank and a dual-branch submodular coverage objective to select streaming video tokens, outperforming training-free baselines.

  2. Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos

    cs.CV 2026-07 conditional novelty 6.5 of 10

    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...

  3. ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding

    cs.CV 2026-07 conditional novelty 6.0 of 10

    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.

  4. FOLIO: Focused Semantic Memory for Streaming Video Understanding

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Entity-centered focus-guided streaming memory lifts Qwen3-VL-8B to 82.0/69.1 Perception/Backward on OVO-Bench and 74.5 on StreamingBench while cutting writer tokens by ~32%.

  5. Learning Streaming Video Representation via Multitask Training

    cs.CV 2025-04 conditional novelty 6.0 of 10

    A causal-temporal-attention video backbone, trained jointly on global, temporal, and spatial visual-language tasks, transfers to multiple streaming video benchmarks with strong efficiency.

  6. LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale

    cs.CV 2025-04 conditional novelty 6.0 of 10

    A video LLM trained on millions of YouTube videos with timestamp-aligned automatic speech recognition transcripts achieves state-of-the-art 7B-scale video QA and wins against 72B models on a custom real-time commentar...

  7. Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark

    cs.CV 2025-04 conditional novelty 6.0 of 10

    Video-MMLU: a 1,065-video lecture benchmark where most AI video models score 10-50%, but text-only models answer 40% of quiz questions without video.

  8. Existence of small semi-vortex solutions for the cubic nonlinear Schr\"{o}dinger system with Rashba type Spin-Orbit coupling on $\mathbb{R}^2$

    math.AP 2026-04 unverdicted novelty 5.0 of 10

    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.

  9. cuRAMSES: Scalable AMR Optimizations for Large-Scale Cosmological Simulations

    astro-ph.GA 2026-04 conditional novelty 5.0 of 10

    Recursive k-section domain decomposition, Morton-key hashing, and GPU dispatch cut communication and memory bottlenecks in RAMSES while preserving conservation to ~0.5%.

Pith tools