WE-MATH benchmark reveals most LMMs rely on rote memorization for visual math while GPT-4o has shifted toward knowledge generalization.
Canonical reference
Visual instruction tuning
Canonical reference. 80% of citing Pith papers cite this work as background.
7
Pith papers citing it
Background
80% of classified citations
citation-role summary
background 5
citation-polarity summary
roles
background 5representative citing papers
HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.
Emu3 shows that next-token prediction on a unified discrete token space for text, images, and video lets a single transformer outperform task-specific models such as SDXL and LLaVA-1.6 in multimodal generation and perception.
VideoPhy benchmark shows state-of-the-art text-to-video models follow physical commonsense and text prompts in only 39.6% of cases for the best model.
OCRBench provides the largest evaluation suite yet for OCR capabilities in large multimodal models, revealing gaps in multilingual, handwritten, and mathematical text handling.
Systematic tests of VLM backbones, policy architectures, and cross-embodiment data yield RoboVLMs that set new SOTA on robot manipulation benchmarks while requiring few manual designs.
E2LLM uses encoder-based soft prompt compression for long contexts to improve LLM reasoning on tasks like summarization and QA while maintaining efficiency.
citing papers explorer
-
We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?
WE-MATH benchmark reveals most LMMs rely on rote memorization for visual math while GPT-4o has shifted toward knowledge generalization.
-
HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.
-
Emu3: Next-Token Prediction is All You Need
Emu3 shows that next-token prediction on a unified discrete token space for text, images, and video lets a single transformer outperform task-specific models such as SDXL and LLaVA-1.6 in multimodal generation and perception.
-
VideoPhy: Evaluating Physical Commonsense for Video Generation
VideoPhy benchmark shows state-of-the-art text-to-video models follow physical commonsense and text prompts in only 39.6% of cases for the best model.
-
OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models
OCRBench provides the largest evaluation suite yet for OCR capabilities in large multimodal models, revealing gaps in multilingual, handwritten, and mathematical text handling.
-
What Matters in Building Vision-Language-Action Models for Generalist Robots
Systematic tests of VLM backbones, policy architectures, and cross-embodiment data yield RoboVLMs that set new SOTA on robot manipulation benchmarks while requiring few manual designs.
-
E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning
E2LLM uses encoder-based soft prompt compression for long contexts to improve LLM reasoning on tasks like summarization and QA while maintaining efficiency.