Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression | Paper Citation Record

Observation f2e20f15-4aad-4c81-b0a3-03c8e487fc4e · outbound

This paper cites On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.878942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 122a4bbf-a213-4606-9a72-c082085fa194 · outbound

This paper cites Flamingo: a Visual Language Model for Few-Shot Learning.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Flamingo: a Visual Language Model for Few-Shot Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.884799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c434291e-f459-4b1d-bc81-80ace33e2e79 · outbound

This paper cites LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.889309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a269769-031b-446a-ab56-b35732429a24 · outbound

This paper cites Longformer: The Long-Document Transformer.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Longformer: The Long-Document Transformer

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.894255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6341cd5-84a7-4958-8a78-81f96c351f18 · outbound

This paper cites Improving language models by retrieving from trillions of tokens.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Improving language models by retrieving from trillions of tokens

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.899006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15780d6a-6352-4f09-bb0f-dccab7448ca6 · outbound

This paper cites Recurrent Memory Transformer.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Recurrent Memory Transformer

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.903759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d570310-1d71-4e50-bece-3d9557364fe9 · outbound

This paper cites Extending Context Window of Large Language Models via Positional Interpolation.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Extending Context Window of Large Language Models via Positional Interpolation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.909045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3579166-3080-4e9b-8a9d-d1cdcf9e3fcb · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.914062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e686ca1f-b861-4b0c-9034-1a07018299c7 · outbound

This paper cites Rethinking Attention with Performers.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Rethinking Attention with Performers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.919179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99a18838-5646-4c0d-9c32-4820b02fbb96 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Training Verifiers to Solve Math Word Problems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.925881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7128fc20-e6ae-41b2-8460-877e3a76ee87 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:05:40.500074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d6a17eba-25ec-4956-bde0-182c2bb964e2 · outbound

This paper cites LongNet: Scaling Transformers to 1,000,000,000 Tokens.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression LongNet: Scaling Transformers to 1,000,000,000 Tokens

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.935471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceee5c42-0271-44a6-bb0f-e56098888641 · outbound

This paper cites LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.940204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a462d50-4ce1-4b4b-8d4e-efb3bd1bf820 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression KTO: Model Alignment as Prospect Theoretic Optimization

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.945289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afdb7c0c-a9ed-4e25-b215-1f9461d4f9f5 · outbound

This paper cites Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.950130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6e19690-de7f-4d81-b8cf-0ca7fe80eba7 · outbound

This paper cites CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.955982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14654f4c-20c9-4633-8e90-bdde020f68cc · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.960902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a305122-6945-4e3b-8c6c-6fb89b8020a2 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.966056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52c18ced-9068-43dd-9e0f-81b5b3f1c1cf · outbound

This paper cites ORPO: Monolithic Preference Optimization without Reference Model.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression ORPO: Monolithic Preference Optimization without Reference Model

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.971671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4c8773b-5102-4e38-89d2-d34bdceea5fb · outbound

This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.977554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4885b889-1337-4d9b-b3d7-29c9536011c9 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:05:40.483715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a91ac6c3-9552-4fed-ae18-c46aa3d840f3 · outbound

This paper cites Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.990379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd698b93-d591-4e94-91ca-a68829c8f023 · outbound

This paper cites LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.995166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c073e57e-692a-41cb-ba7e-1f92411dba3f · outbound

This paper cites Modality-Fair Preference Optimization for Trustworthy MLLM Alignment.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Modality-Fair Preference Optimization for Trustworthy MLLM Alignment

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:38.999608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 408a7ae0-8aa1-497b-8b86-b65caa97e030 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:05:40.469472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c19819d5-e2d7-4672-86bf-0257090288f2 · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.119855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ed4cbcc-c8fc-449f-9e6f-5cdee72dc136 · outbound

This paper cites Generalization through Memorization: Nearest Neighbor Language Models.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Generalization through Memorization: Nearest Neighbor Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.124673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b389be-c157-4fb7-a998-615c3aa76909 · outbound

This paper cites OCR-free Document Understanding Transformer.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression OCR-free Document Understanding Transformer

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.130457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 246c281d-8ea9-41bc-ad28-d4d32daf4b45 · outbound

This paper cites COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.135041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d85ad31-5ab1-44b6-b987-4ac3dd9a3f54 · outbound

This paper cites Reformer: The Efficient Transformer.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Reformer: The Efficient Transformer

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.139785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f79445d-64f0-45ec-be70-5c1f129df163 · outbound

This paper cites Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.144200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ff6b79c-0b16-40a9-8f83-771f85e7c83c · outbound

This paper cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.148919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20c34d17-b4a5-42b8-8d06-671c9f15e81a · outbound

This paper cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.153250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54a80f74-4f8b-4165-bc22-7e7f72374958 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:05:40.455152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cf17794a-01da-46c7-b547-b5673ab6f924 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.161252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 091b3e91-be54-488e-9140-9ff738ad1f71 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:05:40.437989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d6477539-5a82-4112-8942-80d44a97e743 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:05:40.422236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8e0536a6-0da1-49f9-bc31-e33b6a65a278 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 38

Resolution: malformed identifier; no resolver link, observed 2026-08-15T15:05:39.179349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12c064da-f207-4f8c-9140-f88d148e5afe · outbound

This paper cites MemGPT: Towards LLMs as Operating Systems.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression MemGPT: Towards LLMs as Operating Systems

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.183875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 840ab44f-5854-4793-8d1e-0de37425ead1 · outbound

This paper cites YaRN: Efficient Context Window Extension of Large Language Models.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression YaRN: Efficient Context Window Extension of Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.189557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8fb7c0d-3620-4a2a-a09e-bf9c59d43142 · outbound

This paper cites Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.194368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e852ce52-a38a-4cd0-babe-db0526a90792 · outbound

This paper cites Learning Transferable Visual Models From Natural Language Supervision.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Learning Transferable Visual Models From Natural Language Supervision

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.199163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f6da7a0-0b12-4cfe-abf0-5dec3c2bbdb4 · outbound

This paper cites Compressive Transformers for Long-Range Sequence Modelling.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Compressive Transformers for Long-Range Sequence Modelling

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.203992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5f36794-acb0-4324-9901-c5ef471fe993 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.208704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f5ce23e-f39a-4aad-b4a9-db6231dc4522 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:05:40.395155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 742c6bde-89ae-497d-8648-c824cab61b99 · outbound

This paper cites mDPO: Conditional Preference Optimization for Multimodal Large Language Models.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression mDPO: Conditional Preference Optimization for Multimodal Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.218775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24a18a41-7db8-4639-b8b2-f9b0478cfb22 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.223867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21c67e3c-020f-49c5-9493-54af6ee44773 · outbound

This paper cites General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.229824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb0d365f-ad51-4bf2-b850-051cdceb9bac · outbound

This paper cites DeepSeek-OCR: Contexts Optical Compression.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression DeepSeek-OCR: Contexts Optical Compression

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.234732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aec5778d-8dd6-4566-928a-d877fdd3b8b6 · outbound

This paper cites Memorizing Transformers.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Memorizing Transformers

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.239649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1f0b7f0-282c-4737-b84d-147c4bce3e6c · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.244627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2447ec8f-7401-4338-89b7-dd5e46daa117 · outbound

This paper cites Long-Context Language Modeling with Parallel Context Encoding.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Long-Context Language Modeling with Parallel Context Encoding

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.249311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c02db76-1ac1-4e06-9a90-a13a24441e41 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:05:40.379297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 87f4d7bf-7894-4ba3-91b1-23f245ca9462 · outbound

This paper cites an unresolved cited work.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression Unresolved cited work

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.259063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 325650ba-0ed6-4feb-844e-c92b23a3fc48 · outbound

This paper cites From Text to Pixel: Advancing Long-Context Understanding in MLLMs.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression From Text to Pixel: Advancing Long-Context Understanding in MLLMs

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.169449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12f282e6-dd06-4e42-b782-895063f5a505 · outbound

This paper cites arXiv:2601.10378 [cs.CV] https://arxiv.org/abs/2601.10378.

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression arXiv:2601.10378 [cs.CV] https://arxiv.org/abs/2601.10378

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-15T15:05:39.114848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers