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 fine-tuning on multiple existing video datasets.
Kwai keye-vl technical report
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
baseline 2
citation-polarity summary
representative citing papers
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.
OMIBench benchmark reveals that current LVLMs achieve at most 50% on Olympiad problems requiring reasoning across multiple images.
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.
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.
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.
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 agentic tasks.
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.
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.
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-degradation benchmarks.
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.
citing papers explorer
No citing papers match the current filters.