InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs | Paper Citation Record

Observation 58ce4b98-3151-403e-8678-b5cb699491c3 · outbound

This paper cites Janus: Decoupling visual encoding for unified multimodal understanding and generation.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Janus: Decoupling visual encoding for unified multimodal understanding and generation

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.804597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8fd7f759-33e7-475c-9192-79f74b909354 · outbound

This paper cites Emerging Properties in Unified Multimodal Pretraining.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Emerging Properties in Unified Multimodal Pretraining

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.471135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a87d0b9f-bee2-4c42-8203-bd23922d0974 · outbound

This paper cites VILA-U: a unified foundation model integrating visual understanding and generation.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs VILA-U: a unified foundation model integrating visual understanding and generation

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.802514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6b2134b2-ea71-4322-a8bd-a6ba1af188b7 · outbound

This paper cites Harmonizing visual representations for unified multimodal understanding and generation.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Harmonizing visual representations for unified multimodal understanding and generation

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.791680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a93ba93a-5f62-4594-ac70-4734fdbff175 · outbound

This paper cites Ming-univision: Joint image understanding and generation with a unified continuous tokenizer.arXiv preprint arXiv:2510.06590, 2025a.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Ming-univision: Joint image understanding and generation with a unified continuous tokenizer.arXiv preprint arXiv:2510.06590, 2025a

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:10:45.442284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bce5ebb7-6b17-4854-9c77-0b558575a297 · outbound

This paper cites Unitok: A unified tokenizer for visual generation and understanding.arXiv preprint arXiv:2502.20321, 2025a.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Unitok: A unified tokenizer for visual generation and understanding.arXiv preprint arXiv:2502.20321, 2025a

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:10:45.429366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 16d3aa9f-6f7b-4885-a065-99e9b5a2a79f · outbound

This paper cites Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:10:45.419989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 21aa7041-6a31-430c-b826-375928f15e2f · outbound

This paper cites OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:10:45.393690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 34d74abe-0497-4b11-98c8-41dec6369d04 · outbound

This paper cites UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.460863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 668b7147-1e13-4c54-9923-d88565289cde · outbound

This paper cites Show-o2: Improved native unified multimodal models.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Show-o2: Improved native unified multimodal models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.787432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6e7991a9-3bd4-4bd2-a89c-3acd107ba0c1 · outbound

This paper cites UniEval: Unified Holistic Evaluation for Unified Multimodal Understanding and Generation.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs UniEval: Unified Holistic Evaluation for Unified Multimodal Understanding and Generation

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:10:45.390395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 81f9b42e-26d5-4a11-9a60-2812f2d2863b · outbound

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

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs GQA: A new dataset for real-world visual reasoning and compositional question answering

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.783435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d0261ed9-428e-4761-a745-e34cadb8a499 · outbound

This paper cites SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.432288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2766ebe7-d804-4519-8ceb-57a85d2c874c · outbound

This paper cites Evaluating object hallucination in large vision-language models.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Evaluating object hallucination in large vision-language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.793651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 03658430-ab94-4bfe-a54a-5941d7bbec70 · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.464350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1bdb6ec7-6418-4641-8b43-ca29e325fd60 · outbound

This paper cites Mm-vet: Evaluating large multimodal models for integrated capabilities.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Mm-vet: Evaluating large multimodal models for integrated capabilities

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.789390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f2d72a31-ca80-4701-8aa3-cd41697ea66e · outbound

This paper cites Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.736202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 929f172a-908a-4279-b0b6-c6542b092d9a · outbound

This paper cites Geneval: An object-focused framework for evaluating text-to-image alignment.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Geneval: An object-focused framework for evaluating text-to-image alignment

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.738791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ee11affc-1452-4348-b2b3-13d6e7e85949 · outbound

This paper cites Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:10:45.467647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9c2aa275-6840-49f1-90e7-785eb62e1f75 · outbound

This paper cites WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.411067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a53038e8-c08c-4504-a691-32bedb2fb814 · outbound

This paper cites The information bottleneck method.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs The information bottleneck method

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.396288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f1dae431-31f9-43d3-b9d3-86beda9ed022 · outbound

This paper cites Deep learning and the information bottleneck principle.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Deep learning and the information bottleneck principle

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.785420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5f270857-db46-4691-b3cd-05e95079b6c2 · outbound

This paper cites Deep variational information bottleneck.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Deep variational information bottleneck

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.797983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6d2af541-7330-4959-86cd-3ef4665d954e · outbound

This paper cites Revisiting hilbert-schmidt information bottleneck for adversarial robustness.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Revisiting hilbert-schmidt information bottleneck for adversarial robustness

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.778435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dd344693-43cb-4877-8981-26a61d400178 · outbound

This paper cites A survey on multimodal large language models.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs A survey on multimodal large language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.774354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aa14fd1f-e248-4680-8992-01f9c3587c10 · outbound

This paper cites A survey of multimodal learning: Methods, applications, and future.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs A survey of multimodal learning: Methods, applications, and future

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.746935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cf934318-b89e-4d22-b114-ca0794ed1192 · outbound

This paper cites Visual instruction tuning.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Visual instruction tuning

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.740783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fddb9239-9cc8-4a17-bd6b-46eed9030fc5 · outbound

This paper cites Minigpt-4: Enhancing vision-language understanding with advanced large language models.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Minigpt-4: Enhancing vision-language understanding with advanced large language models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.776534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8193229d-05ee-4515-b296-442f52f70349 · outbound

This paper cites Instructblip: Towards general-purpose vision-language models with instruction tuning.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Instructblip: Towards general-purpose vision-language models with instruction tuning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.772232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2ba4ec7f-9de0-4ef6-b083-86933d59ea7b · outbound

This paper cites BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.766406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 927d64dc-afd7-4b8a-ac62-8e4309b7a1b5 · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Flamingo: a visual language model for few-shot learning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.770343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2fecd58e-8f7b-43bc-9af0-6c7c104f465a · outbound

This paper cites Querying as prompt: Parameter-efficient learning for multimodal language model.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Querying as prompt: Parameter-efficient learning for multimodal language model

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.763905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8da7d960-e4cb-4eaf-8c4e-894884976619 · outbound

This paper cites High- resolution image synthesis with latent diffusion models.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs High- resolution image synthesis with latent diffusion models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.762022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 96f3a5a0-a04d-4527-a82f-c758e20b5081 · outbound

This paper cites Scalable diffusion models with transformers.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Scalable diffusion models with transformers

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.768350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a1cea758-471d-4a47-ab00-4f94eb9e6cc7 · outbound

This paper cites Text-to-image Diffusion Models in Generative AI: A Survey.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Text-to-image Diffusion Models in Generative AI: A Survey

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T08:10:45.445484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a5ac7940-a0d4-41ff-b608-f50d1645afd1 · outbound

This paper cites Diffusion-4k: Ultra- high-resolution image synthesis with latent diffusion models.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Diffusion-4k: Ultra- high-resolution image synthesis with latent diffusion models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.780830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bbb82042-0c04-4499-b489-258e7ed117b3 · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.405370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c74b4f1c-bf74-4b2a-9e7b-fb2557d0ca09 · outbound

This paper cites Editar: Unified conditional generation with autoregressive models.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Editar: Unified conditional generation with autoregressive models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.755586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 162561b8-e3bc-4dc0-9713-cf16e2e016ae · outbound

This paper cites Dreamllm: Synergistic multimodal comprehension and creation.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Dreamllm: Synergistic multimodal comprehension and creation

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.757683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f8c49b79-879b-4924-8937-811ff85de83f · outbound

This paper cites Making llama SEE and draw with SEED tokenizer.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Making llama SEE and draw with SEED tokenizer

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.753465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0811652f-8afe-46d0-8b30-a277f7896ff6 · outbound

This paper cites Generative multimodal models are in-context learners.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Generative multimodal models are in-context learners

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.759650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dd5d5985-839d-4291-93b7-1e67630c33c1 · outbound

This paper cites Chameleon: Mixed-Modal Early-Fusion Foundation Models.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Chameleon: Mixed-Modal Early-Fusion Foundation Models

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.438190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 71341f95-6b0e-4021-8355-fc1a89ee0e1d · outbound

This paper cites Fast Autoregressive Models for Continuous Latent Generation.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Fast Autoregressive Models for Continuous Latent Generation

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:10:45.400026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c73ac3a2-42b1-45da-becf-909d8e3220b9 · outbound

This paper cites Emu3: Next-Token Prediction is All You Need.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Emu3: Next-Token Prediction is All You Need

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.453837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bac26ac1-be08-415c-9dd1-0396a829c3e6 · outbound

This paper cites MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:10:45.435592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9ce7f5c3-b503-4397-8d88-24575dcd997c · outbound

This paper cites Growing visual generative capacity for pre-trained mllms.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Growing visual generative capacity for pre-trained mllms

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:10:45.423109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 96348008-d968-42c8-8185-94a74ee37817 · outbound

This paper cites TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T08:10:45.426729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ce74419a-cfe0-465d-bdc3-0d5c16ebb065 · outbound

This paper cites BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.402600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9564809d-8d73-4090-86f8-aff930f992f4 · outbound

This paper cites Qwen2.5 Technical Report.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Qwen2.5 Technical Report

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.383518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1b850180-1e66-439a-bdf5-77e147eef537 · outbound

This paper cites Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:10:45.387048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7647c093-2e30-4c30-9f63-723d791a198c · outbound

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

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs LLaMA: Open and Efficient Foundation Language Models

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.457354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8b9f8907-0f25-46dc-a9a2-5c41beab01f6 · outbound

This paper cites Show-o: One single transformer to unify multimodal understanding and generation.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Show-o: One single transformer to unify multimodal understanding and generation

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.799979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4e99df32-0fe6-4ef7-946f-5a06718290ea · outbound

This paper cites Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.408310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6cac06bd-8777-46db-b8de-10d3e71de603 · outbound

This paper cites Transfusion: Predict the next token and diffuse images with one multi-modal model.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Transfusion: Predict the next token and diffuse images with one multi-modal model

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.795676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4812055c-79b7-4188-82ca-1604e579d2d9 · outbound

This paper cites On variational bounds of mutual information.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs On variational bounds of mutual information

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.749404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a3d8fa67-8548-42b5-a608-00604d9ea937 · outbound

This paper cites Auto-encoding variational bayes.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Auto-encoding variational bayes

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.751544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5e83a1f2-e6a0-4416-bfc0-3efcd66b233b · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Representation Learning with Contrastive Predictive Coding

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.416560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 301102f7-0ed1-4c7a-9843-725a2aef8112 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Imagenet: A large-scale hierarchical image database

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.745019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1418c44d-ca66-42ac-90b4-96d8302f9c50 · outbound

This paper cites Densefusion- 1m: Merging vision experts for comprehensive multimodal perception.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Densefusion- 1m: Merging vision experts for comprehensive multimodal perception

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:10:45.742991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 388417b9-e942-4903-b2e5-7420ab00a381 · outbound

This paper cites Ovis-U1 Technical Report.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Ovis-U1 Technical Report

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:10:45.413995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 61790730-dd59-45b0-b2ef-d2984ff3aae1 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 61

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:10:45.449189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers