SPOT-E uses entropy shaping on answer predictions with low-entropy anchors to optimize visual spotlights at test time via GRPO for better VLM performance on evidence-intensive tasks.
arXiv preprint arXiv:2509.21789 (2025)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3roles
background 2polarities
background 2representative citing papers
SkillGraph jointly evolves agent skills and collaboration topologies in multi-agent vision-language systems using a multimodal graph transformer and a skill designer, yielding consistent performance gains on benchmarks.
Visual attention in MLLMs freezes early during decoding; IVE breaks that inertia by exciting emergent visual tokens and penalizing persistent ones, reducing cognitive relation hallucinations without training.
citing papers explorer
-
SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs
SPOT-E uses entropy shaping on answer predictions with low-entropy anchors to optimize visual spotlights at test time via GRPO for better VLM performance on evidence-intensive tasks.
-
SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology
SkillGraph jointly evolves agent skills and collaboration topologies in multi-agent vision-language systems using a multimodal graph transformer and a skill designer, yielding consistent performance gains on benchmarks.
-
Attention at Rest Stays at Rest: Breaking Visual Inertia for Cognitive Hallucination Mitigation
Visual attention in MLLMs freezes early during decoding; IVE breaks that inertia by exciting emergent visual tokens and penalizing persistent ones, reducing cognitive relation hallucinations without training.