MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models | Paper Citation Record

Observation d4963028-cea7-42fb-85eb-d58299c74469 · outbound

This paper cites Composer: A search framework for hybrid neural architecture design.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Composer: A search framework for hybrid neural architecture design

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee5afdd4-2fad-40fa-95bc-e43deb5fe6c5 · outbound

This paper cites LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a893ae9-1b50-426c-9a26-f288e5ee2d6f · outbound

This paper cites Qwen3-VL Technical Report.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Qwen3-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74fe8b72-f0dd-47a9-8c48-8af1e4b0e80a · outbound

This paper cites Longformer: The Long-Document Transformer.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Longformer: The Long-Document Transformer

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f46d6a71-f30f-4a3e-a6e9-16b47e02561d · outbound

This paper cites WorldSense: A Synthetic Benchmark for Grounded Reasoning in Large Language Models.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models WorldSense: A Synthetic Benchmark for Grounded Reasoning in Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5b1341b-2f75-4af1-bfa9-c06027d4ee2c · outbound

This paper cites Puzzle: Distillation-based nas for inference-optimized llms.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Puzzle: Distillation-based nas for inference-optimized llms

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d18cdb29-e46b-4416-8613-99d02ef4b336 · outbound

This paper cites $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c12516d-c271-43cd-9f96-16f16a517944 · outbound

This paper cites Once-for-all: Train one network and specialize it for efficient deployment.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Once-for-all: Train one network and specialize it for efficient deployment

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ad33f56-95b5-467d-b131-246ceb651600 · outbound

This paper cites Generating Long Sequences with Sparse Transformers.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Generating Long Sequences with Sparse Transformers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cad253a9-6995-4069-8724-96a5a4ddec1e · outbound

This paper cites Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79594ec4-3e9c-4446-ae9f-3f11afb499a2 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dc7213c-40cc-4ed4-b780-133dcd4496a1 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Training Verifiers to Solve Math Word Problems

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d06523f8-ba05-4b70-a4e3-c4d2291c7075 · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bebda3d0-1da3-4448-b0fb-e89f4d254f5e · outbound

This paper cites Nemotron-CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Nemotron-CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5303f941-f4bd-497f-af92-7209ce8da800 · outbound

This paper cites LayerNAS: Neural Architecture Search in Polynomial Complexity.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models LayerNAS: Neural Architecture Search in Polynomial Complexity

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aff1944-1833-48e9-9c65-07d58c43bb72 · outbound

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

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31115c86-e5db-407a-80c0-fc3406cd993b · outbound

This paper cites Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in 10 video analysis.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in 10 video analysis

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a06598b-317e-4566-bc59-9d269a873df6 · outbound

This paper cites Blink: Multimodal large language models can see but not perceive.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Blink: Multimodal large language models can see but not perceive

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30d48631-9e39-401c-a4ef-5c3cd703e333 · outbound

This paper cites Mamba: Linear-time sequence mod- eling with selective state spaces.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Mamba: Linear-time sequence mod- eling with selective state spaces

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b8ebf7d-1915-4347-96e2-fc8455158c3b · outbound

This paper cites Seed1.5-VL Technical Report.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Seed1.5-VL Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf7bc42f-9c7d-4a84-9d9b-8e2dc95790a2 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Measuring Massive Multitask Language Understanding

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cca5df99-1c8c-4737-b8d5-e8282a167574 · outbound

This paper cites Step 3.5 flash: Open frontier-level intelligence with 11b active parameters.arXiv preprint arXiv:2602.10604, 2026.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Step 3.5 flash: Open frontier-level intelligence with 11b active parameters.arXiv preprint arXiv:2602.10604, 2026

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acd11089-d067-4bd6-a987-1d0aef6a56f2 · outbound

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

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e58ce5d1-ea09-4028-8cbc-55e2be4c80c1 · outbound

This paper cites Python-MIP: collection of Python tools for the modeling and solution of mixed-integer linear programs.https://github.com/coin- or/ python-mip, 2023.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Python-MIP: collection of Python tools for the modeling and solution of mixed-integer linear programs.https://github.com/coin- or/ python-mip, 2023

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58406958-4464-4b0b-b303-392159792d84 · outbound

This paper cites Mistral 7B.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Mistral 7B

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d933880-011b-4e0f-8b9d-55efc7c15496 · outbound

This paper cites Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf8d5aea-50d8-486a-82fe-684dbae0a8e8 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Gonzalez, Hao Zhang, and Ion Stoica

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2e2859a-ff26-4a12-af8d-69420f0655d8 · outbound

This paper cites Jamba: Hybrid transformer-mamba language models.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Jamba: Hybrid transformer-mamba language models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e14401c-64c0-47bb-9163-d80145054659 · outbound

This paper cites MiniMax-01: Scaling Foundation Models with Lightning Attention.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models MiniMax-01: Scaling Foundation Models with Lightning Attention

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50eb05b7-5b9b-474b-8925-ca0b2da177f0 · outbound

This paper cites Seed-bench: Bench- marking multimodal large language models.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Seed-bench: Bench- marking multimodal large language models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 409a72a8-48f6-4794-a38c-1fe3dec517d3 · outbound

This paper cites Mvbench: A comprehensive multi-modal video understand- ing benchmark.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Mvbench: A comprehensive multi-modal video understand- ing benchmark

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b436ce7e-b48f-4f5b-a85b-633f9c23e5df · outbound

This paper cites Matvlm: Hybrid mamba-transformer for efficient vision-language modeling.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Matvlm: Hybrid mamba-transformer for efficient vision-language modeling

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ff20684-4e38-4d1d-b018-e8b39c8bb9a9 · outbound

This paper cites ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21d1ab2d-32c1-4969-abed-9392123245db · outbound

This paper cites Jamba: A Hybrid Transformer-Mamba Language Model.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Jamba: A Hybrid Transformer-Mamba Language Model

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff0ab2b0-d38b-426b-9294-f71cdfe9ccf7 · outbound

This paper cites Rea- sonable effectiveness of random weighting: A litmus test for multi-task learning.Transactions on Machine Learning Re- search, 2022.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Rea- sonable effectiveness of random weighting: A litmus test for multi-task learning.Transactions on Machine Learning Re- search, 2022

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ad7d796-80f1-435c-b1fe-9c56bc6d637e · outbound

This paper cites Mmfinereason: Closing the multimodal reason- ing gap via open data-centric methods.arXiv preprint arXiv:2601.21821, 2026.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Mmfinereason: Closing the multimodal reason- ing gap via open data-centric methods.arXiv preprint arXiv:2601.21821, 2026

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 457a882e-c583-4b32-97b6-675b3129c589 · outbound

This paper cites Smooth Tchebycheff Scalarization for Multi-Objective Optimization.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Smooth Tchebycheff Scalarization for Multi-Objective Optimization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb31c01b-472c-403c-9978-9bd5d2b81647 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2362dab7-8237-447b-af30-f14a5d2949a4 · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? InEuropean conference on computer vi- sion, pages 216–233.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Mmbench: Is your multi-modal model an all-around player? InEuropean conference on computer vi- sion, pages 216–233

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff7e6e10-12a2-495d-8b98-b596a87cc98d · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.Advances in neural information processing systems, 35:2507–2521,.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Learn to explain: Multimodal reasoning via thought chains for science question answering.Advances in neural information processing systems, 35:2507–2521,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 242c0021-34cb-45aa-a11d-ed585846ad6e · outbound

This paper cites SmolVLM: Redefining small and efficient multimodal models.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models SmolVLM: Redefining small and efficient multimodal models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e43f924e-0b60-46b8-ad23-2ac55837fa02 · outbound

This paper cites Chartqa: A benchmark for question answer- ing about charts with visual and logical reasoning.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Chartqa: A benchmark for question answer- ing about charts with visual and logical reasoning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e4253cf-c643-4a08-bb07-cfb0eb05af2d · outbound

This paper cites Docvqa: A dataset for vqa on document images.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Docvqa: A dataset for vqa on document images

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e565b46-33fa-4bde-a808-1bb90d99a7d4 · outbound

This paper cites Infographicvqa.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Infographicvqa

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 504477c8-4bd9-413c-8b6c-ae8d84d3af23 · outbound

This paper cites Ocr-vqa: Visual question answering by reading text in images.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Ocr-vqa: Visual question answering by reading text in images

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cf6cbf3-2a65-4fc7-8be7-dfeb32d99b9e · outbound

This paper cites Olmo 3.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Olmo 3

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 740d1109-001e-42c8-baa3-a6d3bd2acd2a · outbound

This paper cites Per- ception test: A diagnostic benchmark for multimodal video models.Advances in Neural Information Processing Sys- tems, 36:42748–42761, 2023.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Per- ception test: A diagnostic benchmark for multimodal video models.Advances in Neural Information Processing Sys- tems, 36:42748–42761, 2023

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7cd3402-e1b8-4612-89bb-e87d7184617f · outbound

This paper cites Rwkv: Reinventing rnns for the transformer era.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Rwkv: Reinventing rnns for the transformer era

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a052a071-aa40-4493-af71-529ee45d1c45 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Learning transferable visual models from natural language supervi- sion

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2de83db1-ff94-4a75-a2ac-32f6c971f8a2 · outbound

This paper cites BOND: Aligning LLMs with Best-of-N Distillation.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models BOND: Aligning LLMs with Best-of-N Distillation

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fa75495-c68c-4416-997a-e156689547e2 · outbound

This paper cites Hardware co-design scaling laws via roofline modelling for on-device llms.arXiv preprint arXiv:2602.10377, 2026.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Hardware co-design scaling laws via roofline modelling for on-device llms.arXiv preprint arXiv:2602.10377, 2026

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6572c381-b2a1-4112-8f00-b81c1b6c547b · outbound

This paper cites Retentive Network: A Successor to Transformer for Large Language Models.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Retentive Network: A Successor to Transformer for Large Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 341ce738-5668-4f74-ad6b-d69550f80144 · outbound

This paper cites Infinitevl: Synergizing linear and sparse attention for highly-efficient, unlimited-input vision-language models.arXiv preprint arXiv:2512.06450, 2025.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Infinitevl: Synergizing linear and sparse attention for highly-efficient, unlimited-input vision-language models.arXiv preprint arXiv:2512.06450, 2025

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67b185ac-4f92-45ff-9857-6e3e85f7ef35 · outbound

This paper cites Kimi Linear: An Expressive, Efficient Attention Architecture.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Kimi Linear: An Expressive, Efficient Attention Architecture

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a03e637a-439e-4d1d-a878-1b4137801d7f · outbound

This paper cites Cambrian-1: A fully open, vision-centric exploration of multimodal llms.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Cambrian-1: A fully open, vision-centric exploration of multimodal llms

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3338cf91-89dc-4eae-89c4-acfe82ef1b18 · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30, 2017.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Attention is all you need.Advances in neural information processing systems, 30, 2017

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f947e670-5a73-4fc9-90be-ec511304a901 · outbound

This paper cites An Empirical Study of Mamba-based Language Models.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models An Empirical Study of Mamba-based Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c910fec7-2b33-4969-bf5a-f74f2509ec99 · outbound

This paper cites Hat: Hardware-aware transformers for efficient natural language processing.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Hat: Hardware-aware transformers for efficient natural language processing

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 197f340a-74a4-46e4-9f13-7eb552dd365f · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 800dac3b-54e0-4329-a832-c2063eee09c1 · outbound

This paper cites Qwen-Image Technical Report.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Qwen-Image Technical Report

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7c4b729-64aa-47bf-892c-d40285fb2ab7 · outbound

This paper cites Rethinking kullback-leibler di- vergence in knowledge distillation for large language mod- els.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Rethinking kullback-leibler di- vergence in knowledge distillation for large language mod- els

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 185e10bb-8fa1-45f5-aee5-7ad9ca4eeac7 · outbound

This paper cites Next-qa: Next phase of question-answering to explaining temporal actions.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Next-qa: Next phase of question-answering to explaining temporal actions

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa74d903-dade-4543-ada5-8c9803c9867f · outbound

This paper cites AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90157096-88ef-4b97-997c-190e3ba79fbe · outbound

This paper cites MSWA: Refining Local Attention with Multi-ScaleWindow Attention.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models MSWA: Refining Local Attention with Multi-ScaleWindow Attention

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e66ccf70-e69a-4c98-afef-33cde19855ef · outbound

This paper cites Gated Delta Networks: Improving Mamba2 with Delta Rule.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Gated Delta Networks: Improving Mamba2 with Delta Rule

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 898056a2-a29f-46cd-86d0-d32bf6e58c0c · outbound

This paper cites Cambrian-S: Towards Spatial Supersensing in Video.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Cambrian-S: Towards Spatial Supersensing in Video

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4366df93-f0d2-42e9-b679-a4d3a808239a · outbound

This paper cites CLEVRER: CoLlision Events for Video REpresentation and Reasoning.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models CLEVRER: CoLlision Events for Video REpresentation and Reasoning

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b365cb0f-aaf4-4d41-8680-88c596f2eb44 · outbound

This paper cites Native sparse attention: Hardware-aligned and natively trainable sparse attention.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Native sparse attention: Hardware-aligned and natively trainable sparse attention

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce4a34a7-3a0c-434f-b97a-f5f862b54f52 · outbound

This paper cites AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e39523aa-4920-493d-ba6c-3ea21ec9ddbc · outbound

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

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for ex- pert agi

Reference 70

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4dab63b-44ff-4d3e-9df7-aa8604d8904b · outbound

This paper cites Hellaswag: Can a machine really finish your sentence? InProceedings of the 57th annual meeting of the association for computational linguistics, pages 4791–4800,.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Hellaswag: Can a machine really finish your sentence? InProceedings of the 57th annual meeting of the association for computational linguistics, pages 4791–4800,

Reference 71

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3a9372c-2042-4926-bd51-fb250e82bc2d · outbound

This paper cites Vision-language models for vision tasks: A survey.IEEE transactions on pattern analysis and machine intelligence, 46(8):5625–5644, 2024.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Vision-language models for vision tasks: A survey.IEEE transactions on pattern analysis and machine intelligence, 46(8):5625–5644, 2024

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a0016f2-4689-447e-a60e-03f98088ac2e · outbound

This paper cites DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae02f27b-2313-4587-b4f1-eab942a93651 · outbound

This paper cites A survey on multi-task learning.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models A survey on multi-task learning

Reference 74

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a74f311-f049-4eb8-ac78-bf0cce34725d · outbound

This paper cites Cobra: Extending mamba to multi-modal large language model for efficient inference.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Cobra: Extending mamba to multi-modal large language model for efficient inference

Reference 75

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5acbdc77-61f1-4b51-8ccd-0e45ea3b79af · outbound

This paper cites AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

Reference 76

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e6c1eb6-3d0a-4e8f-8554-fd73f8a1d567 · outbound

This paper cites Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision.

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision

Reference 77

Resolution: unresolved; no resolver link, observed 2026-07-13T00:53:20.749426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers