A3 reframes dynamic action chunk commitment in VLA models as self-speculative prefix verification, accepting the longest continuous sequence of actions that satisfies consensus-ordered conditional invariance and prefix-closed sequential consistency.
Explain before you answer: A survey on compositional visual reasoning
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Introduces CORTEX benchmark supplying 76,177 validated four-stage diagnostic reasoning traces for open/closed VQA and report generation on chest CT to enable traceable MLLM supervision and evaluation.
DyCo-RL improves four RLVR algorithms on seven visual and math reasoning benchmarks by assigning tokens visual or text roles via Fisher-Rao geodesic distance on attention and reweighting advantages by role-alignment score.
Proposes the Modality Translation Protocol with metrics ToS, CoS, FoS and SSC to quantify visual knowledge bottlenecks in VLMs, plus a Divergence Law hypothesis that scaling language models may increase the penalty.
Mull-Tokens are modality-agnostic latent tokens that enable free-form multimodal thinking and deliver up to 16% gains on spatial reasoning benchmarks.
COMPACT synthesizes compositional visual instruction data to reduce VIT training data by 90% while achieving 100.2% of full performance across eight multimodal benchmarks.
GlowGS improves 3D Gaussian Splatting in nighttime glow scenes via semantic feature generation from diffusion models and novel-view semantic learning with vision foundation models.
Using lexical concreteness to guide contrastive negative mining and a new margin-based Cement loss, the Slipform framework reaches state-of-the-art on compositional benchmarks for vision-language models.
ARIS integrates a graph-based Social World Model, RAG, and agentic architecture for social robots and reports higher user ratings for intelligence, animacy, anthropomorphism, and likeability than an LLM baseline in a 23-person study with the Pepper robot.
citing papers explorer
-
Dynamic Execution Commitment of Vision-Language-Action Models
A3 reframes dynamic action chunk commitment in VLA models as self-speculative prefix verification, accepting the longest continuous sequence of actions that satisfies consensus-ordered conditional invariance and prefix-closed sequential consistency.
-
CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs
Introduces CORTEX benchmark supplying 76,177 validated four-stage diagnostic reasoning traces for open/closed VQA and report generation on chest CT to enable traceable MLLM supervision and evaluation.
-
DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning
DyCo-RL improves four RLVR algorithms on seven visual and math reasoning benchmarks by assigning tokens visual or text roles via Fisher-Rao geodesic distance on attention and reweighting advantages by role-alignment score.
-
The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm
Proposes the Modality Translation Protocol with metrics ToS, CoS, FoS and SSC to quantify visual knowledge bottlenecks in VLMs, plus a Divergence Law hypothesis that scaling language models may increase the penalty.
-
Mull-Tokens: Modality-Agnostic Latent Thinking
Mull-Tokens are modality-agnostic latent tokens that enable free-form multimodal thinking and deliver up to 16% gains on spatial reasoning benchmarks.
-
Visual Compositional Tuning
COMPACT synthesizes compositional visual instruction data to reduce VIT training data by 90% while achieving 100.2% of full performance across eight multimodal benchmarks.
-
GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes
GlowGS improves 3D Gaussian Splatting in nighttime glow scenes via semantic feature generation from diffusion models and novel-view semantic learning with vision foundation models.
-
Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding
Using lexical concreteness to guide contrastive negative mining and a new margin-based Cement loss, the Slipform framework reaches state-of-the-art on compositional benchmarks for vision-language models.
-
ARIS: Agentic and Relationship Intelligence System for Social Robots
ARIS integrates a graph-based Social World Model, RAG, and agentic architecture for social robots and reports higher user ratings for intelligence, animacy, anthropomorphism, and likeability than an LLM baseline in a 23-person study with the Pepper robot.