Paper Citation Record · LEDGER

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models

As of 9 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 2 inbound Pith citation observations for arXiv:2602.23802.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2602.23802 v2

Coverage vector

measured 70 of 70 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T20:14:04.208238Z

measured 72 of 72 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T20:58:30.855338Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T00:49:18.237054Z

Reference resolution

70 of 70 outbound references displayed

verified exact0
verified fuzzy0
unresolved70
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4cd56d96-2b52-4103-a29d-74bb6f807d40 · outbound

This paper cites Qwen2.5-VL Technical Report.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Qwen2.5-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.926761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e6a2209-868a-4065-a677-5949b44dea94 · outbound

This paper cites Chat-based person retrieval via dialogue-refined cross- modal alignment.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Chat-based person retrieval via dialogue-refined cross- modal alignment

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.931853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5f82134-7950-47e0-b50e-59a4701f04db · outbound

This paper cites LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.936058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b031acc-1e60-4a7e-9592-a5d988094944 · outbound

This paper cites SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.940645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b75a2b15-288a-46cc-bfc9-084c113ae010 · outbound

This paper cites Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.944872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 867c155f-91dd-45cd-84de-92652adef16f · outbound

This paper cites Emotion-llama: Multimodal emo- tion recognition and reasoning with instruction tuning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Emotion-llama: Multimodal emo- tion recognition and reasoning with instruction tuning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.948806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c596fe0-263a-40e7-ae4c-fc5c78ff0345 · outbound

This paper cites Emoe: Modality-specific enhanced dynamic emotion experts.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Emoe: Modality-specific enhanced dynamic emotion experts

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.953378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3a43277-9b65-48cc-8d6c-d0ace6ab562c · outbound

This paper cites Catch your emotion: Sharpening emotion perception in multimodal large language models.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Catch your emotion: Sharpening emotion perception in multimodal large language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.957598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69e9830d-e0f9-489f-9055-05e1339ef576 · outbound

This paper cites Video-R1: Reinforcing Video Reasoning in MLLMs.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Video-R1: Reinforcing Video Reasoning in MLLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.962128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c969bbd-7ccb-46ba-894c-6d7ce7317ced · outbound

This paper cites On Designing Effective RL Reward at Training Time for LLM Reasoning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models On Designing Effective RL Reward at Training Time for LLM Reasoning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.966604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 169d64ab-9bc3-4aaa-a3d1-e31d2e091adb · outbound

This paper cites Making the V in VQA matter: Ele- vating the role of image understanding in Visual Question Answering.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Making the V in VQA matter: Ele- vating the role of image understanding in Visual Question Answering

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.970645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e5c2c49-9e68-49f4-821b-c86b13211d03 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.975221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c884e79d-b998-4036-9c26-39a9e3a79689 · outbound

This paper cites Onellm: One framework to align all modalities with language.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Onellm: One framework to align all modalities with language

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.979604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88669c8e-ff9e-460f-a9bc-475363cf071b · outbound

This paper cites Boosting MLLM Reasoning with Text-Debiased Hint-GRPO.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Boosting MLLM Reasoning with Text-Debiased Hint-GRPO

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.983641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09b70d92-c221-4c5d-bb18-351c279dd5fc · outbound

This paper cites Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.988119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 166182ab-f88f-4a23-94be-1b58b69e413f · outbound

This paper cites Learn from downstream and be yourself in multimodal large language model fine-tuning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Learn from downstream and be yourself in multimodal large language model fine-tuning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.992089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b49e719c-bbed-4059-8cbf-2654b980bcec · outbound

This paper cites Be confident: Uncovering overfitting in mllm multi-task tuning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Be confident: Uncovering overfitting in mllm multi-task tuning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:03.995576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f978c6f9-0930-4f9e-9c52-2fafc4da15a5 · outbound

This paper cites Mapo: Mixed advantage policy optimization.arXiv preprint arXiv:2509.18849, 2025.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Mapo: Mixed advantage policy optimization.arXiv preprint arXiv:2509.18849, 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.000130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d0ee372-0197-4789-b5fd-33a3547311bf · outbound

This paper cites Gqa: A new dataset for real-world visual reasoning and compositional question answering.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.004215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ba12ad3-7345-43f1-b9d5-bf74065a11d0 · outbound

This paper cites Learning from teaching reg- ularization: Generalizable correlations should be easy to im- itate.NeurIPS, 37:966–994, 2024.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Learning from teaching reg- ularization: Generalizable correlations should be easy to im- itate.NeurIPS, 37:966–994, 2024

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.014431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b643d058-c196-4ab9-8cf6-775d461e7f7e · outbound

This paper cites Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.018075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f545ca4-f4e5-46f0-8ab6-9fc7b8480e2a · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models LLaVA-OneVision: Easy Visual Task Transfer

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.022097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9ed3b7d-bb1c-48e3-8590-3c8bb8682315 · outbound

This paper cites VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.026500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52a03b49-545a-4add-8801-f2ef62ba0e70 · outbound

This paper cites Mon- key: Image resolution and text label are important things for large multi-modal models.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Mon- key: Image resolution and text label are important things for large multi-modal models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.031632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59cc902c-ffc9-4312-b13e-d044579918a7 · outbound

This paper cites Explainable Multimodal Emotion Recognition.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Explainable Multimodal Emotion Recognition

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.035428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6259af68-65e9-4987-87fb-aeb8c558bf51 · outbound

This paper cites Ex- plainable multimodal emotion reasoning.CoRR, 2023.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Ex- plainable multimodal emotion reasoning.CoRR, 2023

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.040180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53e94391-8752-4c87-91f6-da012278d3c6 · outbound

This paper cites AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.044246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27510ae0-731b-4a09-ba3b-d1d3fa7dfc4a · outbound

This paper cites Lorasculpt: Sculpting lora for harmonizing gen- eral and specialized knowledge in multimodal large language models.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Lorasculpt: Sculpting lora for harmonizing gen- eral and specialized knowledge in multimodal large language models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.049463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5198f810-e98c-4f43-a03b-29e392bb71b6 · outbound

This paper cites Microsoft coco: Common objects in context.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Microsoft coco: Common objects in context

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.053566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2c09ffd-9984-4cc6-8f12-dffbfb00adc5 · outbound

This paper cites Improved baselines with visual instruction tuning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Improved baselines with visual instruction tuning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.057327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e13ce9d-1ac6-4f46-ba5e-ece760393791 · outbound

This paper cites Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.060992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca3dee2f-ea98-4697-b24c-e2cc7392bf62 · outbound

This paper cites DoRA: Weight-Decomposed Low-Rank Adaptation.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models DoRA: Weight-Decomposed Low-Rank Adaptation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.064395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d6b8d6d-4372-4639-b0c1-1623d1bf4361 · outbound

This paper cites GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.067928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 962da5aa-3069-4019-b7c8-bbc4b4b49f14 · outbound

This paper cites Visual-RFT: Visual Reinforcement Fine-Tuning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Visual-RFT: Visual Reinforcement Fine-Tuning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.072542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99ecd203-8520-4069-aa2e-076ab866789e · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.076915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92ee911f-cf4c-47d1-9d89-8c804cb215b8 · outbound

This paper cites ChartQA: A benchmark for question answering about charts with visual and logical reasoning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models ChartQA: A benchmark for question answering about charts with visual and logical reasoning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.080359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aff71ea1-2ca9-4465-803d-97ee918da007 · outbound

This paper cites Con- templating visual emotions: Understanding and overcoming dataset bias.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Con- templating visual emotions: Understanding and overcoming dataset bias

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.083661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27520b90-5628-4f04-b25c-a61d3aa78a1f · outbound

This paper cites A mixed bag of emotions: Model, predict, and transfer emotion distributions.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models A mixed bag of emotions: Model, predict, and transfer emotion distributions

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.087354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bf45be1-2d87-43d4-819e-b047bcce5e4d · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.NeurIPS, 36:53728–53741, 2023.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Direct preference optimization: Your language model is secretly a reward model.NeurIPS, 36:53728–53741, 2023

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.090762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a028c1d-a1f0-43e3-8bb6-79290508172e · outbound

This paper cites Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.093885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4728e5c8-49e0-4840-8f3d-9bea881b4156 · outbound

This paper cites Group robust preference optimization in reward- free rlhf.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Group robust preference optimization in reward- free rlhf

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.097359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4a76982-bab2-4716-b3a1-911f1a06ad74 · outbound

This paper cites Improving LLM-Generated Code Quality with GRPO.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Improving LLM-Generated Code Quality with GRPO

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.101113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c032eb3f-1a85-4ae7-80d9-82f2ad050429 · outbound

This paper cites Backdoor Cleaning without External Guidance in MLLM Fine-tuning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Backdoor Cleaning without External Guidance in MLLM Fine-tuning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.105502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46c5102c-3f2c-401e-89c3-e8042cc4199c · outbound

This paper cites Safegrpo: Self-rewarded mul- timodal safety alignment via rule-governed policy optimiza- tion.arXiv preprint arXiv:2511.12982, 2025.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Safegrpo: Self-rewarded mul- timodal safety alignment via rule-governed policy optimiza- tion.arXiv preprint arXiv:2511.12982, 2025

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.109291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69886bcf-14df-4f05-8660-906311129984 · outbound

This paper cites Proximal Policy Optimization Algorithms.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Proximal Policy Optimization Algorithms

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.113356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e57f08a-bbc3-4180-9778-995074537ebb · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.117269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecce399c-cda8-4b52-b950-650d78ca25d5 · outbound

This paper cites Towards vqa models that can read.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Towards vqa models that can read

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.120825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f372d45e-5e7b-40e5-94aa-87ed35887192 · outbound

This paper cites Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.125091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a3c0ec5-ac01-4374-90f1-de67f8959d2e · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models LLaMA: Open and Efficient Foundation Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.128711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 522417f4-1a78-4044-a568-0fd3d45fca66 · outbound

This paper cites Safety in Large Reasoning Models: A Survey.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Safety in Large Reasoning Models: A Survey

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.132863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22e2dcba-707d-4f81-b689-e8ad3995e6b8 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.136705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59060050-f419-4957-89b1-643d4c823cba · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large lan- guage models.NeurIPS, 35:24824–24837, 2022.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Chain-of-thought prompting elicits reasoning in large lan- guage models.NeurIPS, 35:24824–24837, 2022

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.140872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1e93403-6ca3-4643-ac57-c4e73cf20b0e · outbound

This paper cites Emovit: Revolutionizing emotion insights with vi- sual instruction tuning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Emovit: Revolutionizing emotion insights with vi- sual instruction tuning

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.144878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87fc2543-5052-495c-859b-030fe9d8634d · outbound

This paper cites EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.148188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3df01c42-bc3c-42a3-bcce-7636b9fec44e · outbound

This paper cites Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.152731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 692916be-1ac3-489f-a15d-be3cdbf6720c · outbound

This paper cites Context de-confounded emo- tion recognition.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Context de-confounded emo- tion recognition

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.156268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af7a6d69-2908-4c83-93d8-f171cf81bf40 · outbound

This paper cites Emoset: A large-scale visual emotion dataset with rich attributes.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Emoset: A large-scale visual emotion dataset with rich attributes

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.160499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f35fdd9d-b03b-4a5d-aa92-085b7533807b · outbound

This paper cites EmoLLM: Multimodal Emotional Understanding Meets Large Language Models.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models EmoLLM: Multimodal Emotional Understanding Meets Large Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.163905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 556aad84-e02d-4eb8-89cc-e5b46b98d3bf · outbound

This paper cites Treerpo: Tree relative policy optimization.arXiv preprint arXiv:2506.05183, 2025.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Treerpo: Tree relative policy optimization.arXiv preprint arXiv:2506.05183, 2025

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.167966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f57803f-09a7-4de7-acb0-196233095552 · outbound

This paper cites R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.172212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62ccc93d-2d7e-438a-95c0-4eb85a2c60fa · outbound

This paper cites A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.175590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dcfe257-3936-4fa6-b59a-5fe1adcdfa63 · outbound

This paper cites From image descriptions to visual denotations: New similarity metrics for semantic inference over event descrip- tions.TACL, 2:67–78, 2014.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models From image descriptions to visual denotations: New similarity metrics for semantic inference over event descrip- tions.TACL, 2:67–78, 2014

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.179183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d08763c-cd4f-4ed1-8cd7-fb6ff35ccfcf · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.182502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbd7b248-e55a-4389-b6b7-990c45a2056c · outbound

This paper cites R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.186690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66cb5cf7-9f92-45a8-8ccb-796b1d8260de · outbound

This paper cites Microemo: Time-sensitive multimodal emotion recognition with subtle clue dynamics in video dialogues.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Microemo: Time-sensitive multimodal emotion recognition with subtle clue dynamics in video dialogues

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.190105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d8e9f2e-b3b5-446e-9ad1-4a64d29f34d9 · outbound

This paper cites How Can LLM Guide RL? A Value-Based Approach.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models How Can LLM Guide RL? A Value-Based Approach

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.194029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52018fda-f74d-4068-8447-68a61f8ef8f0 · outbound

This paper cites Facephi: Lightweight multimodal large language model for facial landmark emotion recogni- tion.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Facephi: Lightweight multimodal large language model for facial landmark emotion recogni- tion

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.198029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76d0ea6c-b4c6-4acf-a1aa-53d26834d7d3 · outbound

This paper cites GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.201189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da0ed51d-46e0-4298-a61d-1cb6ba46f34e · outbound

This paper cites R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.204686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c6fc92a-3f10-48c5-9a5d-e03dc2aaa7f9 · outbound

This paper cites Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.208238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation fa78e801-308f-4fc0-9c07-e87da5f93f55 · inbound

EmoTrans: A Benchmark for Understanding, Reasoning, and Predicting Emotion Transitions in Multimodal LLMs cites this paper.

EmoTrans: A Benchmark for Understanding, Reasoning, and Predicting Emotion Transitions in Multimodal LLMs EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-09T02:19:51.159867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 69fc91f4-6db2-471b-96ed-195c024bd24c · inbound

ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection cites this paper.

ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-09T02:19:51.159867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.