REVIEW 19 cited by
R1-Reward: Training Multimodal Reward Model Through Stable 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
R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
read the original abstract
Multimodal Reward Models (MRMs) play a crucial role in enhancing the performance of Multimodal Large Language Models (MLLMs). While recent advancements have primarily focused on improving the model structure and training data of MRMs, there has been limited exploration into the effectiveness of long-term reasoning capabilities for reward modeling and how to activate these capabilities in MRMs. In this paper, we explore how Reinforcement Learning (RL) can be used to improve reward modeling. Specifically, we reformulate the reward modeling problem as a rule-based RL task. However, we observe that directly applying existing RL algorithms, such as Reinforce++, to reward modeling often leads to training instability or even collapse due to the inherent limitations of these algorithms. To address this issue, we propose the StableReinforce algorithm, which refines the training loss, advantage estimation strategy, and reward design of existing RL methods. These refinements result in more stable training dynamics and superior performance. To facilitate MRM training, we collect 200K preference data from diverse datasets. Our reward model, R1-Reward, trained using the StableReinforce algorithm on this dataset, significantly improves performance on multimodal reward modeling benchmarks. Compared to previous SOTA models, R1-Reward achieves a $8.4\%$ improvement on the VL Reward-Bench and a $14.3\%$ improvement on the Multimodal Reward Bench. Moreover, with more inference compute, R1-Reward's performance is further enhanced, highlighting the potential of RL algorithms in optimizing MRMs.
Forward citations
Cited by 19 Pith papers
-
Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs
LMMs perceive videos but underexploit visual content for causal reasoning due to textual shortcuts; ProCauEval diagnoses this and ADPO training reduces reliance on priors.
-
Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learning
Reason-SVG adds a Drawing-with-Thought reasoning stage and GRPO-based reinforcement learning with a hybrid reward to improve LLM and VLM performance on accurate SVG generation.
-
FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification
A self-judging multi-agent VLM injects process-image helpfulness verdicts into tool observations and scales tool rewards by the helpful-call ratio, improving accuracy and tool faithfulness.
-
BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception
BVS combines early-stop attention rollout priors with a scale-aware non-stationary kernel and GP-UCB to locate tiny objects in UHR images more accurately and with fewer MLLM queries than prior visual-search methods.
-
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
DeltaRubric decomposes multimodal preference evaluation into self-generated planning and verification steps within a single model, producing large accuracy improvements on VL-RewardBench via multi-role reinforcement learning.
-
Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models
Introduces VURB benchmark and VUP-35K dataset to train discriminative and generative video reward models that achieve SOTA performance on VURB and VideoRewardBench.
-
Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVR
S-trace adds sparse eligibility traces to RLVR that mask low-entropy tokens, outperforming GRPO by 0.49-3.16% pass@16 on Qwen3 models while improving sample and token efficiency.
-
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
DeScore decouples CoT reasoning from reward scoring in video reward models using a two-stage training process to improve generalization and avoid optimization bottlenecks of coupled generative RMs.
-
See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection
ForeSight lets VLMs use low-level visual cues and mask-based visual feedback within an RL loop to reason more accurately, with the 7B model beating same-scale peers and some closed-source SOTA on a new benchmark.
-
Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models
JRM jointly optimizes preference ranking and language modeling on a shared vision-language backbone, yielding an efficient discriminative reward model that outperforms both discriminative and generative baselines on i...
-
See More, Think Deeper: Query-Expanded Visual Evidence and Answer-Clue Guided Reflection for Long Video Understanding
CoVER framework lets Video-LLMs gather query-expanded visual evidence and verify answers with answer-clue visual feedback to improve long-video understanding.
-
Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning
MARS introduces mono-anchored advantage normalization to quantify information gain from multi-source integration in RLVR, yielding 3.2% and 4.9% gains on GRPO and DAPO.
-
OPERA: An Agent for Image Restoration with End-to-End Joint Planning-Execution Optimization
OPERA jointly optimizes restoration planning via RL over tool compositions and execution via agent-guided co-training of tools, claiming consistent gains over all-in-one models and prior agent methods on multi-degrada...
-
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
DeScore decouples explicit CoT reasoning from reward regression in video reward models via a two-stage cold-start plus dual-objective RL training pipeline.
-
DT2IT-MRM: Debiased Preference Construction and Iterative Training for Multimodal Reward Modeling
DT2IT-MRM proposes a debiased preference construction pipeline, T2I data reformulation, and iterative training to curate multimodal preference data, achieving SOTA on VL-RewardBench, Multimodal RewardBench, and MM-RLH...
-
Reward-Aware Trajectory Shaping for Few-step Visual Generation
RATS lets few-step visual generators surpass multi-step teachers by shaping trajectories with reward-based adaptive guidance instead of strict imitation.
-
StaRPO: Stability-Augmented Reinforcement Policy Optimization
StaRPO improves LLM reasoning by adding autocorrelation function and path efficiency stability metrics to RL policy optimization, yielding higher accuracy and fewer logic errors on reasoning benchmarks.
-
Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation
A capability-oriented multimodal judge benchmark and MCTS-based preference-data generation improve judge models on some benchmarks, but the paper's SOTA claim is not supported by its own numbers.
-
Stabilizing Policy Optimization via Logits Convexity
LCO replaces PPO-style policy gradients with regression toward the advantage-derived optimal logits/policy, restoring logits-level convexity and yielding more stable LLM RL training.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.