Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment | Paper Citation Record

Observation 2036b856-62f4-4b1c-b5d2-dbe80dd4b4e7 · outbound

This paper cites Qwen3-VL Technical Report.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Qwen3-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:24.924803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4717a300-0a56-4541-b646-73bd9e992ac3 · outbound

This paper cites F., Tito, R., Mafla, A., Gomez, L., Rusinol, M., Valveny, E., Jawahar, C., and Karatzas, D.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment F., Tito, R., Mafla, A., Gomez, L., Rusinol, M., Valveny, E., Jawahar, C., and Karatzas, D

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:25.085350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc8c3ff4-281b-47bf-9fad-0f310a01fa16 · outbound

This paper cites an unresolved cited work.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:25.697642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4adbef3-0997-4118-80b9-3fc3c9d87338 · outbound

This paper cites Boundingdocs: a unified dataset for document question answering with spatial annotations: S.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Boundingdocs: a unified dataset for document question answering with spatial annotations: S

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:25.976663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c79a4934-3666-4184-a743-2ee99e67c107 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment LoRA: Low-Rank Adaptation of Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:26.105226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaedfb15-ca91-479b-86df-4c3129ee7264 · outbound

This paper cites Layoutlmv3: Pre-training for document ai with unified text and image masking.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Layoutlmv3: Pre-training for document ai with unified text and image masking

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:26.185055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2a1eabf-7860-4adb-9005-28797899353c · outbound

This paper cites B., and Zhang, K.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment B., and Zhang, K

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:26.305638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e01d50c8-b1d0-4f01-89d7-f736e4cbfdae · outbound

This paper cites 4v (ision) system card https://cdn.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment 4v (ision) system card https://cdn

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:26.440656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 462196c9-676c-458e-bba1-3622dd6bb37c · outbound

This paper cites Docile benchmark for document information localization and extraction.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Docile benchmark for document information localization and extraction

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:26.589095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6494e40-5c51-44a8-8481-2c36e3883896 · outbound

This paper cites Unsloth: Fast fine-tuning and training of llms.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Unsloth: Fast fine-tuning and training of llms

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:26.706633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f53706a9-e410-4714-acf3-b45d8c1c20d0 · outbound

This paper cites A., Jung, K., J \"a lk \"o , J., D’Andecy, V.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment A., Jung, K., J \"a lk \"o , J., D’Andecy, V

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:26.737077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73bcadbe-187f-4e07-97f5-e3da8ea9d093 · outbound

This paper cites Drishtikon: Multi-granular visual grounding for text-rich document images.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Drishtikon: Multi-granular visual grounding for text-rich document images

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:26.773547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2131c131-dfc1-4d60-a3d9-f6d9647d601b · outbound

This paper cites Towards visual grounding: A survey.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Towards visual grounding: A survey

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:26.806212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c91b62c-ff95-4277-ba1e-b3c1c48aecd0 · outbound

This paper cites Docthinker: Explainable multimodal large language models with rule-based reinforcement learning for document understanding.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Docthinker: Explainable multimodal large language models with rule-based reinforcement learning for document understanding

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:26.922461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 343f646b-b3b4-4c6f-9796-5d88adeb675c · outbound

This paper cites Dogr: Towards versatile visual document grounding and referring.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Dogr: Towards versatile visual document grounding and referring

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:26.974062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 881efef6-66ec-4da9-baf2-f95d14aa9d36 · outbound

This paper cites X., Wu, H., Wang, W., Feng, F., Wang, C., Luan, H., and Chua, T.-S.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment X., Wu, H., Wang, W., Feng, F., Wang, C., Luan, H., and Chua, T.-S

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:27.020594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d406b3d1-687d-44c1-b6c5-f9157c4032d9 · outbound

This paper cites A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:27.067817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faaf72c8-c70b-48df-8122-aa6204c9120c · outbound

This paper cites OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:27.102713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2601945-8aa6-4a3e-bfda-40ed08127078 · outbound

This paper cites arXiv preprint arXiv:2504.04974 , year=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment arXiv preprint arXiv:2504.04974 , year=

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:27.131427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2371b19-3b37-43fd-a7f9-b8aa6524e05d · outbound

This paper cites Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:27.252393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8b2dc5d-28dd-4f54-b0c5-edaeb0f13d97 · outbound

This paper cites Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:27.350922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4ce0d30-568d-4922-b27b-bdb39d6b2803 · outbound

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

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:27.404873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49bfeff3-2245-4a6e-8937-3016b5f99916 · outbound

This paper cites SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:27.506499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e956eb2-2da9-4612-9e43-fbb20a34db1a · outbound

This paper cites RL Fine-Tuning Heals OOD Forgetting in SFT.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment RL Fine-Tuning Heals OOD Forgetting in SFT

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:27.583062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fec2b2e4-f917-40a7-81d4-de4e79f26ab0 · outbound

This paper cites Qwen2.5-VL Technical Report.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Qwen2.5-VL Technical Report

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:27.678066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 780c33be-6348-47c9-bfb3-3d95d8b7cfdf · outbound

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

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:27.781991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d300b33e-3241-4d92-b30f-7e733b518ebe · outbound

This paper cites Proceedings of the 30th ACM international conference on multimedia , pages=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Proceedings of the 30th ACM international conference on multimedia , pages=

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:27.897612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 041c6618-0378-4711-b63f-3a4efcce3dc4 · outbound

This paper cites PaddleOCR 3.0 Technical Report.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment PaddleOCR 3.0 Technical Report

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.035910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2115405b-ec84-4213-b783-fee12364c78c · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.204527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 522b424f-c63c-430a-b981-315f58a06ab1 · outbound

This paper cites an unresolved cited work.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Unresolved cited work

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.272655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13c8431a-09e6-43fe-bf40-f1ecb82f34a6 · outbound

This paper cites DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.323502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9432e48e-8716-4962-8802-5ef19a825d05 · outbound

This paper cites Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.375861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9b59ccb-2086-4ed3-9858-5919c10c2246 · outbound

This paper cites Ferret: Refer and Ground Anything Anywhere at Any Granularity.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Ferret: Refer and Ground Anything Anywhere at Any Granularity

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.475131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af234a1e-faf5-40b5-8d18-930e6cf4014f · outbound

This paper cites KOSMOS-2.5: A Multimodal Literate Model.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment KOSMOS-2.5: A Multimodal Literate Model

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.575255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9adb5f5e-4e82-433d-95be-3339e344f9c3 · outbound

This paper cites Farrar, Straus and Giroux , year=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Farrar, Straus and Giroux , year=

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.646952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54621a2c-7471-45b4-94fc-9b72a41f2ae0 · outbound

This paper cites Perception-R1: Pioneering Perception Policy with Reinforcement Learning.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Perception-R1: Pioneering Perception Policy with Reinforcement Learning

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.694126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7419a4c0-5df5-4b11-9c48-0d4ee9eb397d · outbound

This paper cites The Thirty-ninth Annual Conference on Neural Information Processing Systems , year=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment The Thirty-ninth Annual Conference on Neural Information Processing Systems , year=

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.757507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12030f40-4f56-4021-904a-ae70d92b54d8 · outbound

This paper cites arXiv preprint arXiv:2503.20752 , year=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment arXiv preprint arXiv:2503.20752 , year=

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.830889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79ad8275-70e7-4b9b-9103-2f8c9b7edef4 · outbound

This paper cites 2021 , eprint=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment 2021 , eprint=

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.922743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ad47b11-3858-4566-bdcb-edff050db110 · outbound

This paper cites International Conference on Document Analysis and Recognition , pages=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment International Conference on Document Analysis and Recognition , pages=

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:28.996885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5593d532-4328-4f7c-a157-7e8cd098284f · outbound

This paper cites International Conference on Document Analysis and Recognition , pages=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment International Conference on Document Analysis and Recognition , pages=

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.136088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f683b3cf-f5ff-4205-bda7-56c9c97b909c · outbound

This paper cites Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval , pages=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval , pages=

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.294248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa4f7381-55aa-418b-870c-131d313286db · outbound

This paper cites Giovannini et al.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Giovannini et al

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.426738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 701567ac-527d-4b96-8970-565cee502a47 · outbound

This paper cites arXiv e-prints , pages=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment arXiv e-prints , pages=

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.514942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a79af6e-fca0-46a9-bd40-448eb7c6c724 · outbound

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

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Visual-RFT: Visual Reinforcement Fine-Tuning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.557821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96b560bd-7b97-4032-a3a5-ba05062031f3 · outbound

This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.590993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d1271e7-f5f7-4949-82fc-f1c27418339a · outbound

This paper cites VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.636892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1be60655-032b-4dae-8849-3444dc55399e · outbound

This paper cites 2021 , eprint=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment 2021 , eprint=

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.667195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0652bd7b-1633-4164-8c7a-dd63c29e3102 · outbound

This paper cites GitHub repository , howpublished =.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment GitHub repository , howpublished =

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.699471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 090466a4-ad6c-47ec-995c-9690a034761f · outbound

This paper cites Proceedings of the IEEE/CVF international conference on computer vision , pages=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Proceedings of the IEEE/CVF international conference on computer vision , pages=

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.732418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 159a1476-8bce-4e1a-a9b3-9158c145de9e · outbound

This paper cites Towards Visual Grounding: A Survey , year=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment Towards Visual Grounding: A Survey , year=

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.781391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4edaa9f-d5c2-4046-b961-43df417ede1d · outbound

This paper cites arXiv preprint arXiv:2509.10345 , year=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment arXiv preprint arXiv:2509.10345 , year=

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.816900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27bf238b-3274-4a5f-a3da-0091ec70a33b · outbound

This paper cites MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding and Grounding.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding and Grounding

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.847526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f994e11e-2b88-4883-af63-08b7a51a4cb2 · outbound

This paper cites 2025 , eprint=.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment 2025 , eprint=

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:29.882104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers