AI Paper Atlas

Research map / Benchmarks / Perception

Perception leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Perception. Best accuracy: 70.2 (JavisGPT, NeurIPS 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Perception · accuracy

12 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
170.2JavisGPT
Qwen2.5-VL-7B-Instruct
JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
NeurIPS 2025 · Table: Comparison on audio, vi
Multimodal LLMs
267.7ReMoRa
Qwen2-7B
ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding
CVPR 2026 · Table 1
Video-language understanding
366.6ObjectMLLM (LoRA fine-tuned)
VideoLLaMA2-7B
How Can Objects Help Video-Language Understanding?
ICCV 2025 · Table 3
Multimodal LLMs
465.9VideoOrion+
Qwen2-7B
VideoOrion: Tokenizing Object Dynamics in Videos
ICCV 2025 · Table 2
Video-language understanding
563.4VideoChat2-HD-F16 with InternVideo2-s3-1B
Mistral-7B
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
ECCV 2024 · Table 11
Video-language understanding
663.1APPO
Qwen2.5-VL-3B
APPO: Attention-guided Perception Policy Optimization for Video Reasoning
CVPR 2026 · Table 1
Video-language understanding
758.3Divot-LLM
Mistral-7B
Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
CVPR 2025 · Table 3
Video generation
852.1B-VLLMB-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens
ICCV 2025 · Table 1
Video-language understanding
950.6LLaVA-NeXT-Video-AoTD (7B)
LLaVA-NeXT-Video (7B)
Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation
CVPR 2025 · Table 4
Agents, code and math
1048.41MERV (full)
LLaMA-2 7B
Unifying Specialized Visual Encoders for Video Language Models
ICML 2025 · Table 1
Video-language understanding
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.