REVIEW 32 cited by
Perception-R1: Pioneering Perception Policy with Reinforcement Learning
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
Perception-R1: Pioneering Perception Policy with Reinforcement Learning
read the original abstract
Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in MLLM post-training for perception policy learning. While promising, our initial experiments reveal that incorporating a thinking process through RL does not consistently lead to performance gains across all visual perception tasks. This leads us to delve into the essential role of RL in the context of visual perception. In this work, we return to the fundamentals and explore the effects of RL on different perception tasks. We observe that the perceptual complexity is a major factor in determining the effectiveness of RL. We also observe that reward design plays a crucial role in further approching the upper limit of model perception. To leverage these findings, we propose Perception-R1, a scalable RL framework using GRPO during MLLM post-training. With a standard Qwen2.5-VL-3B-Instruct, Perception-R1 achieves +4.2% on RefCOCO+, +17.9% on PixMo-Count, +4.2% on PageOCR, and notably, 31.9% AP on COCO2017 val for the first time, establishing a strong baseline for perception policy learning.
Forward citations
Cited by 32 Pith papers
-
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
P2R decouples perception from reasoning in VLMs via a two-stage process and PRA-GRPO alternating RL training, reporting gains such as 93.2% on V-Star for the 4B model over its Qwen3-VL backbone.
-
CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models
Proposes Spatial Narrative Score (SNS) evaluation for VLMs' camera motion understanding and introduces CaMo model achieving consistent performance on SNS and direct QA.
-
Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era
Formalizes Reasoning Portability (RP) and proposes RDB-CL to modulate per-sample KL regularization in RLVR for MLLM continual learning, achieving +12.0% Last accuracy over vanilla RLVR baseline by preserving reusable ...
-
CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves
CurveBench benchmark reveals that even leading VLMs like Gemini 3.1 Pro reach only 71.1% accuracy recovering containment trees on easy nested-curve images and 19.1% on hard versions, while fine-tuning lifts an open 8B...
-
CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves
CurveBench is a new benchmark for recovering rooted containment trees from images of nested Jordan curves, where the strongest model reaches only 19.1% accuracy on hard cases and fine-tuning lifts an open model to 33....
-
CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding
CGC improves fine-grained multi-image understanding in MLLMs by constructing contrastive training instances from existing single-image annotations and adding a rule-based spatial reward, achieving SOTA on MIG-Bench an...
-
Steadily moving semi-infinite fracture in plane poroelasticity
A new coupled boundary integral method models steadily moving semi-infinite fractures in plane poroelasticity, solving for mechanical deformation and fluid exchange with verification on analytical test cases.
-
V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators
V-Reflection introduces a think-then-look mechanism where MLLM latent states actively interrogate visual features via two-stage distillation from a box-guided teacher to a dynamic autoregressive student, narrowing the...
-
CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning
CamReasoner uses structured O-T-A reasoning and RL on 56k samples to lift camera movement classification from 73.8% to 78.4% and VQA from 60.9% to 74.5% on Qwen2.5-VL-7B.
-
Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning
Zoom-IQA lets a vision-language model iteratively crop and zoom into image regions before giving a quality score, improving reasoning and restoration guidance over single-pass IQA models.
-
ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild
ProAgent uses on-demand tiered perception and context-aware LLM reasoning to deliver proactive assistance on AR glasses, achieving up to 27.7% higher prediction accuracy and 20.5% lower false detections than baselines.
-
VIDEOP2R: Video Understanding from Perception to Reasoning
VideoP2R separates perception and reasoning in a process-aware RFT pipeline with a new CoT dataset and PA-GRPO rewards, reaching SOTA on six of seven video benchmarks.
-
CodePercept: Code-Grounded Visual STEM Perception for MLLMs
Perception, not reasoning, is the main bottleneck for MLLM STEM visual reasoning, and training on executable reconstruction code measurably fixes it.
-
IoUPD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models
Ground-truth boxes, when used as a privileged visual hint for a frozen teacher during training, improve autoregressive visual grounding in multimodal LLMs by about 4 Acc@0.7 points with no inference-time overhead.
-
DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences
Rule-reward training on controllable cross-video differences (Grounding + MCQ) improves Video MLLM local spatiotemporal evidence localization and transfers to general video QA benchmarks.
-
Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization
GCPO performs per-token credit assignment in discrete policy optimization by setting token advantages proportional to the difference in model predictions under positive versus negative prompts, outperforming GRPO and ...
-
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation
VideoSeeker integrates agentic reasoning and visual prompts into LVLMs via automated data synthesis, cold-start supervision, and RL training, yielding +13.7% gains on instance-level video tasks over baselines includin...
-
Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
SCOLAR addresses information gain collapse in latent visual reasoning by generating independent auxiliary visual tokens from LLM hidden states, extending acceptable CoT length over 30x and achieving +14.12% gains on b...
-
Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
SCOLAR fixes information gain collapse in latent visual reasoning by generating independent auxiliary visual tokens via a detransformer, extending acceptable CoT length over 30x and delivering +14.12% gains on reasoni...
-
Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression
A plug-and-play RL method adds batch-level distributional supervision via CCC rewards to reduce regression-to-the-mean in MLLMs on imbalanced regression benchmarks.
-
Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression
A Group Relative Policy Optimization framework with concordance correlation coefficient rewards improves MLLM regression accuracy on long-tailed distributions, especially in medium- and few-shot regimes, without model...
-
SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models
SSL-R1 reformulates visual SSL tasks into verifiable puzzles to supply rewards for RL post-training of MLLMs, yielding gains on multimodal benchmarks without external supervision.
-
RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension
RefBench-PRO organizes REC into attribute, position, interaction, relation, commonsense, and reject tasks; no tested MLLM exceeds 72%, and Ref-R1 raises Qwen2.5-VL-7B from 57.6 to 69.4 on it.
-
Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment
For document visual grounding at 4B scale, reasoning-free GRPO training outperforms a reasoning-enabled variant, and the reasoning variant compresses its traces during training.
-
From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models
The survey formalizes MLLM perception as a unified vision-language capability and traces its evolution via a new five-stage taxonomy while outlining future challenges.
-
Steadily moving semi-infinite fracture in plane poroelasticity
XEmbodied achieves SOTA on 18 embodied VQA benchmarks by fusing 3D geometric tokens and distilled physical cues into a 30B VLM with progressive curriculum training.
-
Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
HDPO reframes tool efficiency as a conditional objective within accurate trajectories, enabling Metis to reduce tool invocations by orders of magnitude while raising reasoning accuracy.
-
PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment
By gating the reinforcement-learning reward on a binary visual-fidelity score, PaLMR lifts Qwen2.5-VL-7B to 70.9 on HallusionBench and 59.3 on MMMU, surpassing its GRPO baseline.
-
Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?
Longer textual reasoning chains degrade MLLM accuracy on fine-grained visual tasks; a new normalization and constrained-reward training framework mitigates the effect and sets new SOTA numbers.
-
OneThinker: All-in-one Reasoning Model for Image and Video
OneThinker unifies image and video reasoning in one model across 10 tasks via a 600k corpus, CoT-annotated SFT, and EMA-GRPO reinforcement learning, reporting strong results on 31 benchmarks plus some cross-task transfer.
-
XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments
XEmbodied is a foundation model that integrates 3D geometric and physical signals into VLMs using a 3D Adapter and Efficient Image-Embodied Adapter, plus progressive curriculum and RL post-training, to improve spatial...
-
Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning
A pipeline of chain-of-thought data synthesis, LoRA-based supervised fine-tuning, rejection sampling, and rule-based reinforcement learning raises multi-image grounding accuracy by 9.04% on MIG-Bench and 4.41% on aver...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.