Paper Citation Record · LEDGER

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward

As of 22 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2411.18654.

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

pith.paper-citation-record.v1
2411.18654 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T11:36:36.447560Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

43 of 43 outbound references displayed

verified exact0
verified fuzzy21
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 11bf1fa5-15d6-4f09-a254-22732f9f8bad · outbound

This paper cites GPT-4 Technical Report.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.261063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fabde44-4aa1-4b20-b3d5-a424287e8d50 · outbound

This paper cites Text2action: Generative adversarial synthesis from language to action.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Text2action: Generative adversarial synthesis from language to action

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.266346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9f58cfb-5d48-4a1e-b980-266b26f6b36f · outbound

This paper cites Lan- guage2pose: Natural language grounded pose forecasting.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Lan- guage2pose: Natural language grounded pose forecasting

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:37.023300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3431954e-fd16-4365-8ae5-9c0a8f8e14a1 · outbound

This paper cites The claude 3 model family: Opus, sonnet, haiku.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward The claude 3 model family: Opus, sonnet, haiku

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:37.008372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 22bf2dd3-5534-4c52-8e7f-c6e802725e47 · outbound

This paper cites Teach: Temporal action composition for 3d hu- mans.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Teach: Temporal action composition for 3d hu- mans

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.995311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d2d71697-00b5-41b9-91b2-be0cd0f417f8 · outbound

This paper cites A general theoretical paradigm to un- derstand learning from human preferences.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward A general theoretical paradigm to un- derstand learning from human preferences

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.983538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b7bbcdb7-2317-4288-8a50-45d50897d641 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.288168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cfeecc8-d8ed-45fc-adda-9f34d03667cd · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Constitutional AI: Harmlessness from AI Feedback

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.292953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 434cfae0-4860-4c9f-beb2-614a961bfc45 · outbound

This paper cites Executing your commands via motion diffusion in latent space.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Executing your commands via motion diffusion in latent space

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.971641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b4f73b8d-a44e-4ea5-84fd-12975e111df2 · outbound

This paper cites Synthesis of compositional animations from textual descriptions.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Synthesis of compositional animations from textual descriptions

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.952416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 74fde757-2ee4-456a-aafb-921d7082eeab · outbound

This paper cites Generating diverse and natural 3d human motions from text.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Generating diverse and natural 3d human motions from text

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.938738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f71c9262-418f-4c31-b48e-b8312b3b95df · outbound

This paper cites Tm2t: Stochastic and tokenized modeling for the reciprocal genera- tion of 3d human motions and texts.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Tm2t: Stochastic and tokenized modeling for the reciprocal genera- tion of 3d human motions and texts

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.927067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1d05a900-6a4c-4208-a9da-b7fcbedbba8c · outbound

This paper cites Momask: Generative masked model- ing of 3d human motions.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Momask: Generative masked model- ing of 3d human motions

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.915154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1a9974c6-6310-44f8-ba60-3d10974bd890 · outbound

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

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward LoRA: Low-Rank Adaptation of Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.317715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8af7188d-997e-4fec-9fe8-becbb2bde81c · outbound

This paper cites Motiongpt: Human motion as a foreign lan- guage.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Motiongpt: Human motion as a foreign lan- guage

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.897806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c3fc2729-1403-4374-8447-255e388724d6 · outbound

This paper cites Aligning Text-to-Image Models using Human Feedback.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Aligning Text-to-Image Models using Human Feedback

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.326120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0585130f-c05b-43ab-8599-4bfeb6fea469 · outbound

This paper cites Baton: Aligning text-to-audio model with human prefer- ence feedback.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Baton: Aligning text-to-audio model with human prefer- ence feedback

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.885297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation aac945af-18f9-40c3-87b7-46c32ae6e3c6 · outbound

This paper cites Generating animated videos of human activities from natural language descrip- tions.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Generating animated videos of human activities from natural language descrip- tions

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.872437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0d314363-fbb6-4997-9d98-7883127114e3 · outbound

This paper cites Peft: State- of-the-art parameter-efficient fine-tuning methods.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Peft: State- of-the-art parameter-efficient fine-tuning methods

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.855613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 46d475d0-efae-4274-a0d9-58b9b4a36d0a · outbound

This paper cites Learning Generalizable Human Motion Generator with Reinforcement Learning.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Learning Generalizable Human Motion Generator with Reinforcement Learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.343250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2595e5e-c029-4f96-8858-74ff827152dc · outbound

This paper cites Gpt-4 technical report, 2024.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Gpt-4 technical report, 2024

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.841501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 670e0b1f-cd9c-47d3-bd67-0011be59e58b · outbound

This paper cites Training language models to follow instructions with human feedback.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Training language models to follow instructions with human feedback

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.351404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b1dfac4-df7f-471f-813e-1027c524cb76 · outbound

This paper cites MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.354927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15b80d2a-3d79-4b4e-88a3-7cfdcc6c6568 · outbound

This paper cites Black, and G ¨ul Varol.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Black, and G ¨ul Varol

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.818678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3fc11818-74d7-4f01-8406-d61cac75e70e · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Direct preference optimization: Your language model is secretly a reward model

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.362862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa99a03d-8533-40f4-b015-9b0ecf1185db · outbound

This paper cites Proximal Policy Optimization Algorithms.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Proximal Policy Optimization Algorithms

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.365791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69d572c7-78d9-4753-b5fa-2ee51e1ce13f · outbound

This paper cites Human Motion Diffusion Model.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Human Motion Diffusion Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.370247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a417bf18-83c2-483b-862f-5f0a7ee0e4a7 · outbound

This paper cites Human Motion Diffusion as a Generative Prior.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Human Motion Diffusion as a Generative Prior

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.375237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8039d85a-016b-4e8b-9f2b-d42f29d463b6 · outbound

This paper cites Exploring text-to-motion generation with human preference.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Exploring text-to-motion generation with human preference

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.797778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c35c5f8c-672b-4815-9723-ea2ad1a812d5 · outbound

This paper cites Motionclip: Exposing human motion generation to clip space.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Motionclip: Exposing human motion generation to clip space

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.383735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d088b05-92da-4506-a208-bf1406735105 · outbound

This paper cites MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.387786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d993d3e2-3e27-4042-8d3f-42c7e1ba1d5f · outbound

This paper cites Imagere- ward: Learning and evaluating human preferences for text- to-image generation.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Imagere- ward: Learning and evaluating human preferences for text- to-image generation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.392207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b9cc144-599f-4fab-b0ce-1e617172c4ee · outbound

This paper cites Generating human motion from textual descrip- tions with discrete representations.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Generating human motion from textual descrip- tions with discrete representations

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.769754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2fbc7b1d-4244-4c2e-bdb0-39b6f6fbb6ca · outbound

This paper cites MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.400357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18c2c780-c64c-42c3-a58e-1de0b174fe78 · outbound

This paper cites Re- modiffuse: Retrieval-augmented motion diffusion model.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Re- modiffuse: Retrieval-augmented motion diffusion model

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.404294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 942cb4b9-3563-4e3e-be0e-60173e01bcf4 · outbound

This paper cites Temo: Towards text-driven 3d stylization for multi-object meshes.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Temo: Towards text-driven 3d stylization for multi-object meshes

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.747450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 908931f4-5777-4768-a9c5-6f632332c655 · outbound

This paper cites SLiC-HF: Sequence Likelihood Calibration with Human Feedback.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward SLiC-HF: Sequence Likelihood Calibration with Human Feedback

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.413997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dad936b6-a080-4587-af88-6414f678f295 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Fine-Tuning Language Models from Human Preferences

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T11:36:36.419130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00b8d620-29e3-4d29-9485-f571aeb7138d · outbound

This paper cites a person walks forward, turns around, walks backward, and then squats.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward a person walks forward, turns around, walks backward, and then squats

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.733152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e64b8865-d3dd-4c7c-b32e-6c13f8f85542 · outbound

This paper cites Event1, Conjunction1, Event2, Conjunction2, ..., Conjunction4, Event5.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Event1, Conjunction1, Event2, Conjunction2, ..., Conjunction4, Event5

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.719831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cc51935b-4dad-4109-bd7e-2a0ca69bcbf6 · outbound

This paper cites an unresolved cited work.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-12T11:36:36.707831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b4ba40b3-3891-44de-8fdb-70985b24f8d9 · outbound

This paper cites an unresolved cited work.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-12T11:36:36.696250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 82c50662-6178-4bc1-97b1-2bd30c6f5148 · outbound

This paper cites Equivalent Quality.

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Equivalent Quality

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:36:36.680469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Pith citing papers

No inbound Pith citation observations are available.