Laser reformulates visual reasoning via Dynamic Windowed Alignment Learning to maintain latent superposition of global features, delivering 5.03% average gains over Monet and over 97% fewer inference tokens on six benchmarks.
Eyes wide shut? exploring the visual shortcomings of multimodal llms
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
dataset 1
method 1
citation-polarity summary
representative citing papers
Public defenders view AI as most useful for evidence investigation but limited in courtroom work and strategy, with adoption blocked by costs, confidentiality risks, and norms, requiring human oversight and open development.
An RL-based questioner agent adaptively generates queries to discover novel failure modes in VLMs without human intervention.
Seed1.8 is a new foundation model that adds unified agentic capabilities for search, code execution, and GUI interaction to existing LLM and vision strengths.
LENS is a new multi-level benchmark dataset for evaluating MLLMs on perception-to-reasoning tasks using the same images across all levels with recent social media content.
Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.
citing papers explorer
-
Forest Before Trees: Latent Superposition for Efficient Visual Reasoning
Laser reformulates visual reasoning via Dynamic Windowed Alignment Learning to maintain latent superposition of global features, delivering 5.03% average gains over Monet and over 97% fewer inference tokens on six benchmarks.
-
How Can AI Augment Access to Justice? Public Defenders' Perspectives on AI Adoption
Public defenders view AI as most useful for evidence investigation but limited in courtroom work and strategy, with adoption blocked by costs, confidentiality risks, and norms, requiring human oversight and open development.
-
Discovering Failure Modes in Vision-Language Models using RL
An RL-based questioner agent adaptively generates queries to discover novel failure modes in VLMs without human intervention.
-
Seed1.8 Model Card: Towards Generalized Real-World Agency
Seed1.8 is a new foundation model that adds unified agentic capabilities for search, code execution, and GUI interaction to existing LLM and vision strengths.
-
LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models
LENS is a new multi-level benchmark dataset for evaluating MLLMs on perception-to-reasoning tasks using the same images across all levels with recent social media content.
-
Seed1.5-VL Technical Report
Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.