REVIEW 32 cited by
T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
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
T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
read the original abstract
Recent advancements in large language models have demonstrated how chain-of-thought (CoT) and reinforcement learning (RL) can improve performance. However, applying such reasoning strategies to the visual generation domain remains largely unexplored. In this paper, we present T2I-R1, a novel reasoning-enhanced text-to-image generation model, powered by RL with a bi-level CoT reasoning process. Specifically, we identify two levels of CoT that can be utilized to enhance different stages of generation: (1) the semantic-level CoT for high-level planning of the prompt and (2) the token-level CoT for low-level pixel processing during patch-by-patch generation. To better coordinate these two levels of CoT, we introduce BiCoT-GRPO with an ensemble of generation rewards, which seamlessly optimizes both generation CoTs within the same training step. By applying our reasoning strategies to the baseline model, Janus-Pro, we achieve superior performance with 13% improvement on T2I-CompBench and 19% improvement on the WISE benchmark, even surpassing the state-of-the-art model FLUX.1. Code is available at: https://github.com/CaraJ7/T2I-R1
Forward citations
Cited by 32 Pith papers
-
Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist
Arena-T2I Hard benchmark with ~30 decomposed constraints per prompt and a dependency-aware checklist reward yields better faithfulness-aesthetics trade-off than single-reward or weighted-sum baselines on SD3.5-Medium ...
-
MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation
MetaPoint represents 2D coordinates as special tokens in visual generative models to enable precise spatial control using existing positional encodings without architectural modifications.
-
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
RankE co-evolves AR policy and decoder via alternating ranking optimization, improving both FID and CLIP scores on LlamaGen-XL and Janus-Pro where policy-only RL degrades FID.
-
AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment
AutoRubric-T2I learns and selects explicit rubrics from preference pairs to guide VLM judges, producing high-quality interpretable rewards for T2I alignment with far less data than traditional Bradley-Terry models.
-
AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment
AutoRubric-T2I learns a small set of interpretable rubrics for VLM judges that outperform scalar reward models on T2I benchmarks while using far less preference data.
-
OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
OmniNFT introduces modality-wise advantage routing, layer-wise gradient surgery, and region-wise loss reweighting in an online diffusion RL framework to improve audio-video quality, alignment, and synchronization.
-
UniPath: Adaptive Coordination of Understanding and Generation for Unified Multimodal Reasoning
UniPath adaptively models coordination-path diversity in unified multimodal models by training a path-conditioned executor and using a lightweight planner for input-dependent selection, improving performance over fixe...
-
SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models
SOAR is a reward-free on-policy method that supplies dense per-timestep supervision to correct exposure bias in diffusion model denoising trajectories, raising GenEval from 0.70 to 0.78 and OCR from 0.64 to 0.67 over ...
-
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning
Process-driven image generation decomposes text-to-image synthesis into interleaved cycles of textual planning, visual drafting, textual reflection, and visual refinement with dense consistency supervision.
-
Demystifying Video Reasoning
Video diffusion models perform reasoning primarily along denoising steps via multi-path exploration and convergence (Chain-of-Steps), not sequential frames, with emergent memory, self-correction, and layer specialization.
-
MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition
MICo-150K is a new 150K-image dataset with 7 tasks, a De&Re real-image subset, MICo-Bench, and Weighted-Ref-VIEScore metric that improves AI models for generating consistent composites from arbitrary numbers of refere...
-
PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation
PortraitGen integrates real-image exemplars into GRPO sampling and applies dual rewards (OmniReward and AI-Portrait) to improve photorealism, claiming better results than baselines on a new PortraitBench.
-
GenClaw: Code-Driven Agentic Image Generation
GenClaw introduces a three-stage code-driven workflow for agentic image generation that inserts programmatic sketches between linguistic reasoning and pixel synthesis.
-
SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations
SynAE is a multi-metric framework that evaluates how well synthetic benchmarks replicate real data characteristics for multi-turn tool-calling agent testing.
-
Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning
CLVR couples verified logical planning with pixel diffusion, uses proxy reinforcement learning on distilled histories, and merges weights to cut inference to 4 NFEs while outperforming open-source T2I models on comple...
-
Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning
CLVR framework adds closed-loop visual verification, proxy prompt reinforcement learning, and delta-space weight merge to improve complex text-to-image generation over single-step or unverified multi-step baselines.
-
Cutting rules in strong field QED with application to trident pair production
A Veltman-style cutting equation for plane-wave QED is formulated and used to relate two-loop elastic electron scattering corrections to the trident rate in a constant crossed field, with a spin-resolved analytical ra...
-
Cutting rules in strong field QED with application to trident pair production
Cutting rules for strong-field QED are formulated and used to relate higher-loop corrections to trident pair production, yielding a spin-resolved analytical rate expression in constant crossed fields.
-
Meta-CoT: Enhancing Granularity and Generalization in Image Editing
Meta-CoT uses two-level decomposition of editing operations into meta-tasks and a CoT consistency reward to improve granularity and generalization, reporting 15.8% gains across 21 tasks.
-
MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation
MAR-GRPO stabilizes GRPO for AR-diffusion hybrids via multi-trajectory expectation and uncertainty-based token selection, yielding better visual quality, stability, and spatial understanding than baselines.
-
Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward
Saliency-R1 uses a novel saliency map technique and GRPO with human bounding-box overlap as reward to improve VLM reasoning faithfulness and interpretability.
-
Demystifying Video Reasoning
Video diffusion models reason along the denoising trajectory (Chain-of-Steps), not primarily across frames, and this mechanism can be nudged by ensembling latent trajectories.
-
From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation
EG-GRPO improves autoregressive text-to-image models by reallocating RL updates according to token entropy, excluding low-entropy tokens from reward signals while adding entropy bonuses to high-entropy ones, yielding ...
-
RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection
RL-RIG uses a generate-reflect-edit loop with reinforcement learning to improve spatial accuracy in image generation, reporting up to 11% gains over prior open-source models on scene-graph metrics.
-
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
-
MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning
MathVis-Fine proposes a dataset with fine-grained visual annotations and dependency ratings plus a progressive two-stage training paradigm to align visual supervision with sample-specific necessity in multimodal mathe...
-
UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation
UniCanvas introduces a diffusion-based approach for unified multimodal generation by embedding text as visual patterns within images on a shared canvas.
-
Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
BiDPO extends Diffusion DPO to bimodal preferences and adds region-aware guidance, improving compositional fidelity in text-to-image generation over prior methods.
-
PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
A data-generation pipeline plus pairwise subject-consistency rewards in RL improve consistency and prompt adherence for multi-subject personalized image generation.
-
OmniGen2: Towards Instruction-Aligned Multimodal Generation
OmniGen2 introduces a unified generative model with two distinct decoding pathways and a decoupled image tokenizer that achieves competitive results on text-to-image and editing benchmarks plus state-of-the-art consis...
-
Toward Native Multimodal Modeling: A Roadmap
A roadmap that defines architectural nativity for multimodal models and categorizes them into Multi-to-Text, Multi-to-Target, and Multi-to-Multi types while outlining an industrial pipeline toward unified transformer-...
-
A Survey of Reinforcement Learning for Large Reasoning Models
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.