REVIEW 17 cited by
Explain Before You Answer: A Survey on Compositional Visual Reasoning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Explain Before You Answer: A Survey on Compositional Visual Reasoning
read the original abstract
Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference. While early surveys focus on monolithic vision-language models or general multimodal reasoning, a dedicated synthesis of the rapidly expanding compositional visual reasoning literature is still missing. We fill this gap with a comprehensive survey spanning 2023 to 2025 that systematically reviews 260+ papers from top venues (CVPR, ICCV, NeurIPS, ICML, ACL, etc.). We first formalize core definitions and describe why compositional approaches offer advantages in cognitive alignment, semantic fidelity, robustness, interpretability, and data efficiency. Next, we trace a five-stage paradigm shift: from prompt-enhanced language-centric pipelines, through tool-enhanced LLMs and tool-enhanced VLMs, to recently minted chain-of-thought reasoning and unified agentic VLMs, highlighting their architectural designs, strengths, and limitations. We then catalog 60+ benchmarks and corresponding metrics that probe compositional visual reasoning along dimensions such as grounding accuracy, chain-of-thought faithfulness, and high-resolution perception. Drawing on these analyses, we distill key insights, identify open challenges (e.g., limitations of LLM-based reasoning, hallucination, a bias toward deductive reasoning, scalable supervision, tool integration, and benchmark limitations), and outline future directions, including world-model integration, human-AI collaborative reasoning, and richer evaluation protocols. By offering a unified taxonomy, historical roadmap, and critical outlook, this survey aims to serve as a foundational reference and inspire the next generation of compositional visual reasoning research.
Forward citations
Cited by 17 Pith papers
-
CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs
CORTEX supplies structured four-stage diagnostic traces for 3D chest CT MLLMs, generated via frontier LLMs and verified through automated rubrics plus radiologist review on the CT-RATE dataset.
-
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 prefi...
-
Dynamic Execution Commitment of Vision-Language-Action Models
A3 determines the execution horizon in VLA models as the longest prefix of actions that passes consensus-based verification and sequential consistency checks.
-
Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification
Rule-VLN is the first large-scale benchmark injecting 177 regulatory categories into an urban environment, and the proposed SNRM module equips pre-trained VLN agents with zero-shot semantic reasoning and detour planni...
-
Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification
Rule-VLN injects 177 regulatory signs into Touchdown-scale urban graphs; SNRM’s VLM perception plus mental-map detours cuts constraint violations ~19% and raises task completion ~6% zero-shot.
-
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.
-
Dynamic Execution Commitment of Vision-Language-Action Models
A3 adaptively sets a VLA model's execution horizon to the longest action prefix the model re-confirms under conditional and sequential re-decoding, matching or improving task success without manual tuning.
-
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.
-
Dynamic Execution Commitment of Vision-Language-Action Models
A3 adaptively selects verifiable action prefixes in VLA models using group-sampled consensus and conditional re-decoding to balance robustness and speed without manual horizon tuning.
-
The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm
Vision-language models exhibit functional blindness by exploiting language priors over visual representations; the Modality Translation Protocol and metrics like Toll, Curse, and Fallacy of Seeing reveal this, support...
-
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.
-
VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning
Fine-tuning Qwen2.5-VL on VisReason, a 489K-example multi-round visual chain-of-thought dataset (165K with pseudo-depth), modestly improves LLM-judged visual reasoning scores, with caveats about self-referential 3D ev...
-
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 ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.