VLRS-Bench is the first benchmark dedicated to complex vision-language reasoning in remote sensing, with 2000 QA pairs across 14 tasks in cognition, decision, and prediction dimensions.
The llama 3 herd of models.arXiv e-prints, pages arXiv–2407
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
M³KG-RAG improves multimodal reasoning in large language models by constructing multi-hop knowledge graphs and selectively pruning retrieved context with GRASP.
ProcObject-10K is the first benchmark for object-centric procedural reasoning in videos that exposes a large gap where models answer questions plausibly but fail to ground their answers in the correct video segments.
SWIM aligns cross-attention maps from object nouns to ground-truth masks during training on the new NL-Refer dataset to enable text-only fine-grained video object understanding in MLLMs.
LaviGen turns 3D generative models into an autoregressive layout generator that models geometric and physical constraints, delivering 19% higher physical plausibility and 65% faster inference on the LayoutVLM benchmark.
SpeciaRL applies a dynamic verifier-based reward in reinforcement learning to steer reasoning LMMs toward correct and specific predictions on fine-grained open-world image classification tasks.
A three-stage pipeline uses few-shot VLM action parsing, sliding-window segmentation, and LLM sequence classification with peer context to measure student engagement from classroom videos.
An RL-trained lightweight agent uses MLLM perceptual rewards to perform efficient label-free image restoration, matching SOTA on full-reference metrics and surpassing prior work on no-reference metrics.
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.
citing papers explorer
-
VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing
VLRS-Bench is the first benchmark dedicated to complex vision-language reasoning in remote sensing, with 2000 QA pairs across 14 tasks in cognition, decision, and prediction dimensions.
-
M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation
M³KG-RAG improves multimodal reasoning in large language models by constructing multi-hop knowledge graphs and selectively pruning retrieved context with GRASP.
-
ProcObject-10K: Benchmarking Object-Centric Procedural Understanding in Instructional Videos
ProcObject-10K is the first benchmark for object-centric procedural reasoning in videos that exposes a large gap where models answer questions plausibly but fail to ground their answers in the correct video segments.
-
See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding
SWIM aligns cross-attention maps from object nouns to ground-truth masks during training on the new NL-Refer dataset to enable text-only fine-grained video object understanding in MLLMs.
-
Repurposing 3D Generative Model for Autoregressive Layout Generation
LaviGen turns 3D generative models into an autoregressive layout generator that models geometric and physical constraints, delivering 19% higher physical plausibility and 65% faster inference on the LayoutVLM benchmark.
-
Specificity-aware reinforcement learning for fine-grained open-world classification
SpeciaRL applies a dynamic verifier-based reward in reinforcement learning to steer reasoning LMMs toward correct and specific predictions on fine-grained open-world image classification tasks.
-
Context Matters: Peer-Aware Student Behavioral Engagement Measurement via VLM Action Parsing and LLM Sequence Classification
A three-stage pipeline uses few-shot VLM action parsing, sliding-window segmentation, and LLM sequence classification with peer context to measure student engagement from classroom videos.
-
Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback
An RL-trained lightweight agent uses MLLM perceptual rewards to perform efficient label-free image restoration, matching SOTA on full-reference metrics and surpassing prior work on no-reference metrics.
-
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.