MirrorBench reveals that leading MLLMs perform far below humans on tasks requiring self-referential perception and representation, even at the simplest level.
Navbench: Probing multimodal large language models for embodied navigation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
A group-revision paradigm for GRPO-based RL fine-tuning of VLMs converts failure responses into improvement signals that refine rewards and advantages, yielding gains on referring segmentation, REC, and counting benchmarks.
SAGE trains agents in physics-grounded semantic abstractions via RL with asymmetric clipping, achieving 53.21% LLM-Match Success on A-EQA (+9.7% over baseline) and encouraging physical robot transfer.
MapTab introduces a 328-map, 196,800-query benchmark showing that current multimodal LLMs fall far short on multi-criteria route planning from maps-plus-tables.
Proposes cost-aware question selection for ambiguous object navigation via information-gain analysis on corpora, a cost-penalizing benchmark, and a zero-shot MLLM agent.
citing papers explorer
-
MirrorBench: Evaluating Self-centric Intelligence in MLLMs by Introducing a Mirror
MirrorBench reveals that leading MLLMs perform far below humans on tasks requiring self-referential perception and representation, even at the simplest level.
-
From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding
A group-revision paradigm for GRPO-based RL fine-tuning of VLMs converts failure responses into improvement signals that refine rewards and advantages, yielding gains on referring segmentation, REC, and counting benchmarks.
-
Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation
SAGE trains agents in physics-grounded semantic abstractions via RL with asymmetric clipping, achieving 53.21% LLM-Match Success on A-EQA (+9.7% over baseline) and encouraging physical robot transfer.
-
MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs
MapTab introduces a 328-map, 196,800-query benchmark showing that current multimodal LLMs fall far short on multi-criteria route planning from maps-plus-tables.
-
Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation
Proposes cost-aware question selection for ambiguous object navigation via information-gain analysis on corpora, a cost-penalizing benchmark, and a zero-shot MLLM agent.