Pith. sign in

REVIEW 12 cited by

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 2507.01949 v1 pith:HD53LQPH submitted 2025-07-02 cs.CV

Kwai Keye-VL Technical Report

classification cs.CV
keywords keye-vlcapabilitiesmodelvideowhilealignmentdatahigh-quality
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form videos, a dominant medium in today's digital landscape. To bridge this gap, we introduce \textbf{Kwai Keye-VL}, an 8-billion-parameter multimodal foundation model engineered for leading-edge performance in short-video understanding while maintaining robust general-purpose vision-language abilities. The development of Keye-VL rests on two core pillars: a massive, high-quality dataset exceeding 600 billion tokens with a strong emphasis on video, and an innovative training recipe. This recipe features a four-stage pre-training process for solid vision-language alignment, followed by a meticulous two-phase post-training process. The first post-training stage enhances foundational capabilities like instruction following, while the second phase focuses on stimulating advanced reasoning. In this second phase, a key innovation is our five-mode ``cold-start'' data mixture, which includes ``thinking'', ``non-thinking'', ``auto-think'', ``think with image'', and high-quality video data. This mixture teaches the model to decide when and how to reason. Subsequent reinforcement learning (RL) and alignment steps further enhance these reasoning capabilities and correct abnormal model behaviors, such as repetitive outputs. To validate our approach, we conduct extensive evaluations, showing that Keye-VL achieves state-of-the-art results on public video benchmarks and remains highly competitive on general image-based tasks (Figure 1). Furthermore, we develop and release the \textbf{KC-MMBench}, a new benchmark tailored for real-world short-video scenarios, where Keye-VL shows a significant advantage.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

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

  1. PEDESTRIANQA: A Benchmark for Vision-Language Models on Pedestrian Intention and Trajectory Prediction

    cs.CV 2026-05 unverdicted novelty 7.0

    PedestrianQA is a new benchmark that turns pedestrian behavior prediction into VLM question-answering with rationales, reporting improved intention classification, trajectory accuracy, and explanation quality after fi...

  2. HoloCount: A Holistic Visual Counting Benchmark for MLLMs

    cs.CV 2026-07 conditional novelty 6.0

    HoloCount is a three-tier visual counting benchmark showing that MLLMs fail systematically on analytical reasoning, high-density scenes, and linguistic prior conflicts, with even the best models dropping below 50% acc...

  3. Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts

    cs.CV 2026-05 unverdicted novelty 6.0

    Chart-FR1 uses Focus-CoT for linking reasoning to visual cues and Focus-GRPO reinforcement learning with efficiency rewards to outperform prior MLLMs on dense chart reasoning tasks.

  4. OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model

    cs.CV 2026-04 unverdicted novelty 6.0

    OMIBench benchmark reveals that current LVLMs achieve at most 50% on Olympiad problems requiring reasoning across multiple images.

  5. Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization

    cs.CV 2026-04 unverdicted novelty 6.0

    MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.

  6. Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing

    cs.CV 2026-03 conditional novelty 6.0

    PaddleOCR-VL uses a Valid Region Focus Module to select key visual tokens and a 0.9B model for guided recognition, delivering SOTA document parsing with far fewer tokens and parameters.

  7. Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach

    cs.SD 2025-09 unverdicted novelty 6.0

    A zero-training VLM framework generates music from images via ABC notation, multi-modal RAG, and self-refinement while providing text and visual explanations for the outputs.

  8. InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

    cs.CV 2025-08 unverdicted novelty 6.0

    InternVL3.5 advances open-source multimodal models with Cascade RL for +16% reasoning gains and ViR for 4x inference speedup, with the 241B model reaching SOTA among open-source MLLMs on multimodal, reasoning, and age...

  9. PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning

    cs.CL 2025-08 unverdicted novelty 6.0

    PEER applies GRPO reinforcement learning with a unified process-outcome reward model to structured empathetic reasoning steps on the SER dataset, yielding gains in empathy, strategy alignment, and human-likeness.

  10. Swift Sampling: Selecting Temporal Surprises via Taylor Series

    cs.CV 2026-05 unverdicted novelty 5.0

    Swift Sampling is a training-free frame selection method that uses Taylor expansions on video latent trajectories to pick temporally surprising frames, outperforming uniform sampling on long-video QA tasks.

  11. OPERA: An Agent for Image Restoration with End-to-End Joint Planning-Execution Optimization

    cs.CV 2026-05 unverdicted novelty 5.0

    OPERA jointly optimizes restoration planning via RL over tool compositions and execution via agent-guided co-training of tools, claiming consistent gains over all-in-one models and prior agent methods on multi-degrada...

  12. Kwai Keye-VL-2.0 Technical Report

    cs.CV 2026-06 unverdicted novelty 4.0

    Kwai Keye-VL-2.0-30B-A3B is a 30B MoE model with 3B active parameters using DSA adaptation and MOPD distillation that reports SOTA results on video understanding and agent benchmarks.