Paper Citation Record · LEDGER

LLMs can see and hear without any training

As of 10 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 4 inbound Pith citation observations for arXiv:2501.18096.

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

pith.paper-citation-record.v1
2501.18096 v1

Coverage vector

measured 64 of 64 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T00:46:08.276886Z

measured 68 of 68 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:41:39.719320Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-16T17:53:11.781235Z

Reference resolution

64 of 64 outbound references displayed

verified exact0
verified fuzzy36
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 07461521-f5d5-4dbc-ba99-b9eca04c3b9d · outbound

This paper cites write newline.

LLMs can see and hear without any training write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:07.963230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f40734fc-2f39-4238-b0e9-b4ac7c89a2c0 · outbound

This paper cites Pixtral 12B.

LLMs can see and hear without any training Pixtral 12B

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:07.970023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f5ce520-c345-42cb-8b39-daedf969618c · outbound

This paper cites SPICE : S emantic propositional image caption evaluation.

LLMs can see and hear without any training SPICE : S emantic propositional image caption evaluation

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.269755Z

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 259fe07d-7b7f-43c5-89ef-e5b091e28ad5 · outbound

This paper cites and Lavie, A.

LLMs can see and hear without any training and Lavie, A

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.253716Z

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 f7f04a0f-559b-4c16-a6f7-d1f502c76582 · outbound

This paper cites Improving image generation with better captions.

LLMs can see and hear without any training Improving image generation with better captions

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.237162Z

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 cb5f418e-b65d-4717-9e60-9717e8746d21 · outbound

This paper cites W., Fidler, S., and Kreis, K.

LLMs can see and hear without any training W., Fidler, S., and Kreis, K

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:07.991979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d80eda5-09d1-4c14-a4db-130921020026 · outbound

This paper cites Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack.

LLMs can see and hear without any training Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:07.998074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67571005-a8df-4362-aab6-cacfa53cad31 · outbound

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

LLMs can see and hear without any training Imagenet: A large-scale hierarchical image database

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.004275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ec30906-4b7d-4993-9436-66a84a2a57e2 · outbound

This paper cites Clotho: An audio captioning dataset.

LLMs can see and hear without any training Clotho: An audio captioning dataset

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.197196Z

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 8c0cfefa-d255-443d-87bb-1d43bbba6d22 · outbound

This paper cites The Llama 3 Herd of Models.

LLMs can see and hear without any training The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.017455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d19565a3-573a-4ece-93c4-787d72b96cfe · outbound

This paper cites M., Jain, A., Schmidt, L., Toshev, A., and Shankar, V.

LLMs can see and hear without any training M., Jain, A., Schmidt, L., Toshev, A., and Shankar, V

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.181512Z

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 8dda7dcb-7a38-4118-9091-8a4fc12923ac · outbound

This paper cites Interpreting the Second-Order Effects of Neurons in CLIP.

LLMs can see and hear without any training Interpreting the Second-Order Effects of Neurons in CLIP

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.028501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24436c06-49ae-487f-bbbd-1af9ed9e7331 · outbound

This paper cites A Neural Algorithm of Artistic Style.

LLMs can see and hear without any training A Neural Algorithm of Artistic Style

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.033691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee6ca5fe-c59e-4946-ab2d-0d88b34aa8a9 · outbound

This paper cites On the content bias in fr \'e chet video distance.

LLMs can see and hear without any training On the content bias in fr \'e chet video distance

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.165970Z

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 54066178-ac0e-4576-b742-67253af18245 · outbound

This paper cites F., Ellis, D.

LLMs can see and hear without any training F., Ellis, D

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.150324Z

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 bfefb861-2462-44e1-91b4-ca65e854ed40 · outbound

This paper cites V., Joulin, A., and Misra, I.

LLMs can see and hear without any training V., Joulin, A., and Misra, I

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.132059Z

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 da8027aa-beb1-4bf2-a24d-36f98151b87b · outbound

This paper cites S., Shah, A., Yin, X., Parikh, D., and Misra, I.

LLMs can see and hear without any training S., Shah, A., Yin, X., Parikh, D., and Misra, I

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.052450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdd064a1-cf92-4143-9fd5-2bf110ec5155 · outbound

This paper cites Mmg-ego4d: Multimodal generalization in egocentric action recognition.

LLMs can see and hear without any training Mmg-ego4d: Multimodal generalization in egocentric action recognition

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.106134Z

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 2aa4606c-ac40-4d58-b040-be7ec5246a39 · outbound

This paper cites Audioclip: Extending clip to image, text and audio.

LLMs can see and hear without any training Audioclip: Extending clip to image, text and audio

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.091082Z

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 0741e06d-d761-4090-95da-3600bbee57e9 · outbound

This paper cites Imagen Video: High Definition Video Generation with Diffusion Models.

LLMs can see and hear without any training Imagen Video: High Definition Video Generation with Diffusion Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.066514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20abe8e5-1b44-4608-a80a-2f1ca44b0f92 · outbound

This paper cites Openclip, 2021.

LLMs can see and hear without any training Openclip, 2021

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.074929Z

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 50a54a14-ec58-44f2-b3be-4933370cbdc2 · outbound

This paper cites Rethinking fid: Towards a better evaluation metric for image generation.

LLMs can see and hear without any training Rethinking fid: Towards a better evaluation metric for image generation

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.059583Z

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 e327ff0a-71c0-455a-8b32-53de2061b349 · outbound

This paper cites Mistral 7B.

LLMs can see and hear without any training Mistral 7B

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.081016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e04e41e-d73b-49e9-a3d0-baeb2bf2f162 · outbound

This paper cites and Fei-Fei, L.

LLMs can see and hear without any training and Fei-Fei, L

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.044785Z

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 45df32dc-b331-40fc-8f74-81b7e508733e · outbound

This paper cites What do we learn from inverting CLIP models?.

LLMs can see and hear without any training What do we learn from inverting CLIP models?

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.090384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45345009-5da6-443e-8f01-318e7bb14201 · outbound

This paper cites Pick-a-pic: An open dataset of user preferences for text-to-image generation.

LLMs can see and hear without any training Pick-a-pic: An open dataset of user preferences for text-to-image generation

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.028909Z

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 50f1f474-5d21-4fa5-9df9-987b465c0df9 · outbound

This paper cites S., Reid, M., Matsuo, Y., and Iwasawa, Y.

LLMs can see and hear without any training S., Reid, M., Matsuo, Y., and Iwasawa, Y

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:09.012021Z

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 688e3352-7798-4a11-b2f5-d99be38bd7b3 · outbound

This paper cites Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities.

LLMs can see and hear without any training Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.997000Z

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 36a6ddfb-a057-4d2b-b35b-cbcf5ab1102b · outbound

This paper cites an unresolved cited work.

LLMs can see and hear without any training Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-10T00:46:08.977632Z

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 52c1ea4a-947f-4dd1-ad4c-5160baaccb34 · outbound

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

LLMs can see and hear without any training Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.961288Z

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 ac1e12be-fce0-4996-a55a-dcd92156cbe6 · outbound

This paper cites M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning.

LLMs can see and hear without any training M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.118465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaddedd7-5f35-4e5b-9764-503fad42fcb9 · outbound

This paper cites DeCap : D ecoding CLIP latents for zero-shot captioning via text-only training.

LLMs can see and hear without any training DeCap : D ecoding CLIP latents for zero-shot captioning via text-only training

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.945732Z

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 14a4ec48-b4ce-41cd-b469-16522d447a2b · outbound

This paper cites an unresolved cited work.

LLMs can see and hear without any training Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.128461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cbe38f1-f7c2-43ad-ad6f-6b85627af581 · outbound

This paper cites Flow Matching for Generative Modeling.

LLMs can see and hear without any training Flow Matching for Generative Modeling

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.133554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34264a0c-d475-4189-b526-fced26b8aac1 · outbound

This paper cites Improving Text-to-Image Consistency via Automatic Prompt Optimization.

LLMs can see and hear without any training Improving Text-to-Image Consistency via Automatic Prompt Optimization

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.138982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 593a6f57-3e95-44bb-a976-34d8cea1126d · outbound

This paper cites Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities.

LLMs can see and hear without any training Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.143919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1033a21d-83e2-4edf-aeba-44da51e4bdd5 · outbound

This paper cites How T o100 M : L earning a T ext- V ideo E mbedding by W atching H undred M illion N arrated V ideo C lips.

LLMs can see and hear without any training How T o100 M : L earning a T ext- V ideo E mbedding by W atching H undred M illion N arrated V ideo C lips

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.917534Z

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 aa943601-8824-46bc-8f50-368d8e29c6bf · outbound

This paper cites Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention.

LLMs can see and hear without any training Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.153195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 396a3532-bf3b-4daf-a936-b2a2bd6c225c · outbound

This paper cites H., Seybold, B., Hauth, A., Manen, S., Sun, C., and Schmid, C.

LLMs can see and hear without any training H., Seybold, B., Hauth, A., Manen, S., Sun, C., and Schmid, C

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.902188Z

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 5dddf899-95dd-414b-b6d0-038afb215443 · outbound

This paper cites an unresolved cited work.

LLMs can see and hear without any training Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-10T00:46:08.885727Z

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 10d47875-b6e7-4f60-83ca-41e7e4e945bf · outbound

This paper cites Introducing openai o1-preview.

LLMs can see and hear without any training Introducing openai o1-preview

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.867355Z

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 b7918d94-7097-4632-a4d4-a19cd2c21e94 · outbound

This paper cites BLEU : A method for automatic evaluation of machine translation.

LLMs can see and hear without any training BLEU : A method for automatic evaluation of machine translation

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.849424Z

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 c4876983-387a-4576-a046-bea434a1ba8d · outbound

This paper cites Movie Gen: A Cast of Media Foundation Models.

LLMs can see and hear without any training Movie Gen: A Cast of Media Foundation Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.177469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d52ba24e-5c4a-4635-ac20-4c094d5ec01d · outbound

This paper cites W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., and Sutskever, I.

LLMs can see and hear without any training W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., and Sutskever, I

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.182174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9baacafb-a287-4ef2-b54d-1cbb561e5bed · outbound

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

LLMs can see and hear without any training Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.186659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa7d852a-d09a-49d4-bb44-801c457c92ca · outbound

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

LLMs can see and hear without any training High-resolution image synthesis with latent diffusion models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.191571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0874f5f2-fb01-4a21-af90-4158959c883e · outbound

This paper cites L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., Ho, J., Fleet, D.

LLMs can see and hear without any training L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., Ho, J., Fleet, D

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.812005Z

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 7728eb58-c5f2-4394-9cd9-8e7d72f1312f · outbound

This paper cites Zero-shot audio captioning with audio-language model guidance and audio context keywords.

LLMs can see and hear without any training Zero-shot audio captioning with audio-language model guidance and audio context keywords

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.796723Z

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 566a6112-59e8-49d9-b567-3629ee02ecd8 · outbound

This paper cites Zero-Shot Audio Captioning via Audibility Guidance.

LLMs can see and hear without any training Zero-Shot Audio Captioning via Audibility Guidance

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.205600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da075a6e-f406-4cee-b340-a85ccdcbdc6c · outbound

This paper cites H., Tan, H., Bansal, M., Rohrbach, A., Chang, K.-W., Yao, Z., and Keutzer, K.

LLMs can see and hear without any training H., Tan, H., Bansal, M., Rohrbach, A., Chang, K.-W., Yao, Z., and Keutzer, K

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.780741Z

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 266e9844-c78d-4d8b-9996-41f9ca698977 · outbound

This paper cites Emu edit: Precise image editing via recognition and generation tasks.

LLMs can see and hear without any training Emu edit: Precise image editing via recognition and generation tasks

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.764846Z

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 93a29c0a-a145-4515-bed3-dfa693881bb7 · outbound

This paper cites and Zisserman, A.

LLMs can see and hear without any training and Zisserman, A

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.220243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f0924f5-8430-486a-9718-8c1f6a86e3d4 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

LLMs can see and hear without any training Gemma: Open Models Based on Gemini Research and Technology

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.224799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45254f0e-ab4f-49be-85de-a6f2c7572252 · outbound

This paper cites Zerocap: Zero-shot image-to-text generation for visual-semantic arithmetic.

LLMs can see and hear without any training Zerocap: Zero-shot image-to-text generation for visual-semantic arithmetic

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.738738Z

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 5138eade-5d48-4783-bde5-0238c7b8605c · outbound

This paper cites CIDEr : C onsensus-based image description evaluation.

LLMs can see and hear without any training CIDEr : C onsensus-based image description evaluation

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.724624Z

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 ba63aaaa-e306-448c-9b55-4807c0e9e945 · outbound

This paper cites Internvid: A large-scale video-text dataset for multimodal understanding and generation.

LLMs can see and hear without any training Internvid: A large-scale video-text dataset for multimodal understanding and generation

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.708850Z

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 3c11ff3c-043c-47d7-b8b2-5a1e44f33196 · outbound

This paper cites V., Zhou, D., et al.

LLMs can see and hear without any training V., Zhou, D., et al

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.692953Z

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 44818b35-f4e7-42e0-bd36-ffc37988b3c4 · outbound

This paper cites E., Huang, P.-Y., Howes, R., Sharma, V., Li, S.-W., Ghosh, G., Zettlemoyer, L., and Feichtenhofer, C.

LLMs can see and hear without any training E., Huang, P.-Y., Howes, R., Sharma, V., Li, S.-W., Ghosh, G., Zettlemoyer, L., and Feichtenhofer, C

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.675933Z

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 dc653a20-dfca-4130-9302-d9e9532d66bb · outbound

This paper cites MSR-VTT : A large video description dataset for bridging video and language.

LLMs can see and hear without any training MSR-VTT : A large video description dataset for bridging video and language

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.660540Z

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 69bb8738-4a48-403b-ab0e-cbe856820531 · outbound

This paper cites V., Zhou, D., and Chen, X.

LLMs can see and hear without any training V., Zhou, D., and Chen, X

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.645005Z

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 3c9f03ad-4cec-483f-ad2e-a15fc1827c61 · outbound

This paper cites ConZIC : Controllable zero-shot image captioning by sampling-based polishing.

LLMs can see and hear without any training ConZIC : Controllable zero-shot image captioning by sampling-based polishing

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.630321Z

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 4ed7780e-fb70-4000-b3f7-e11c6360ea04 · outbound

This paper cites Meacap: Memory-augmented zero-shot image captioning.

LLMs can see and hear without any training Meacap: Memory-augmented zero-shot image captioning

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.614899Z

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 fc8b6ceb-0b37-4262-907d-dc8bf1a118a5 · outbound

This paper cites Sigmoid loss for language image pre-training.

LLMs can see and hear without any training Sigmoid loss for language image pre-training

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-10T00:46:08.272230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88cde246-7d4e-4957-9ac3-b77d3112e4f5 · outbound

This paper cites a henb \.

LLMs can see and hear without any training a henb \

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:46:08.588755Z

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.

Pith citing papers

Observation 07f8e3c3-0c4b-49da-9c4b-4fc59bc741a6 · inbound

SmartAvatar: Text- and Image-Guided Human Avatar Generation with VLM AI Agents cites this paper.

SmartAvatar: Text- and Image-Guided Human Avatar Generation with VLM AI Agents LLMs can see and hear without any training

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T10:41:39.719320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 234690bb-8c5c-4572-865e-afc404bf07a3 · inbound

Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models cites this paper.

Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models LLMs can see and hear without any training

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T20:49:43.276306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7cc7435-15c9-461a-aad3-117776b30975 · inbound

It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models cites this paper.

It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models LLMs can see and hear without any training

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-16T17:53:11.782964Z

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 03fd9dca-c859-42c1-bd48-dfcfb2d0f5bb · inbound

Personalizing Text-to-Image Generation to Individual Taste cites this paper.

Personalizing Text-to-Image Generation to Individual Taste LLMs can see and hear without any training

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T05:26:02.475416Z

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.