CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining | Paper Citation Record

Observation 7bd41ea1-fded-4706-a238-697e91a2981e · outbound

This paper cites Big vision.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Big vision

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.316088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7ee11045-bf6a-4a87-b6a7-108aa68eb244 · outbound

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

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:27:36.903981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 58d325f0-6ec9-4a7f-80fc-b8ec4c002598 · outbound

This paper cites JAX: composable transformations of Python+NumPy programs.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining JAX: composable transformations of Python+NumPy programs

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.249407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a337a850-aeb6-4fdc-b08b-b6d5812b12c0 · outbound

This paper cites Internvl: Scaling up vision foun- dation models and aligning for generic visual-linguistic tasks.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Internvl: Scaling up vision foun- dation models and aligning for generic visual-linguistic tasks

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.288198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bb933ee7-ea04-4cc2-9e95-743713968bb8 · outbound

This paper cites Reproducible scaling laws for contrastive language- image learning.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Reproducible scaling laws for contrastive language- image learning

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.331038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f8efb56c-a83c-46eb-b1e3-ad0c2d3a5113 · outbound

This paper cites Dif- fusion policy: Visuomotor policy learning via action diffusion.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Dif- fusion policy: Visuomotor policy learning via action diffusion

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.314279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5167d138-83dd-4a06-858c-1588e01c6c2d · outbound

This paper cites author Dong, W.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining author Dong, W

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T08:27:36.448205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5fa29b93-1576-40c1-86c3-ca6ba4a7d7ad · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining An image is worth 16x16 words: Transformers for image recognition at scale

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.357613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b898bb92-15c7-4289-97f9-6a08e5b0ce7b · outbound

This paper cites Eva: Exploring the limits of masked visual representation learning at scale.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Eva: Exploring the limits of masked visual representation learning at scale

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.343081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 67131aa8-f0a7-49ea-838e-4e193ed5fcd8 · outbound

This paper cites Eva-02: A visual represen- tation for neon genesis.Image and Vision Computing, 149:105171.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Eva-02: A visual represen- tation for neon genesis.Image and Vision Computing, 149:105171

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.307229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9e1fdcae-4494-4c42-a320-d0e9b8d50d4f · outbound

This paper cites Act3d: 3d feature field transform- ers for multi-task robotic manipulation.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Act3d: 3d feature field transform- ers for multi-task robotic manipulation

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.313442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 88193174-f803-4904-88ea-86de96acbe9e · outbound

This paper cites Revisiting point cloud shape classification with a simple and effective baseline.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Revisiting point cloud shape classification with a simple and effective baseline

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.355423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 32c09b2c-dc2d-4826-9468-7af6653f0cb2 · outbound

This paper cites Rvt: Robotic view transformer for 3d object manipulation.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Rvt: Robotic view transformer for 3d object manipulation

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.339217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4f3fda71-5160-4826-99aa-162edb970956 · outbound

This paper cites Learning dense visual descriptors using image augmentations for robot manipulation tasks.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Learning dense visual descriptors using image augmentations for robot manipulation tasks

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.304933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d8850130-7c24-4f2d-8cf7-b11361967db8 · outbound

This paper cites Pct: Point cloud transformer.Computational visual media, 7(2): 187–199.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Pct: Point cloud transformer.Computational visual media, 7(2): 187–199

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.325048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e5cc3937-0a6b-476e-9f3b-8a1b2722eb1e · outbound

This paper cites Mvtn: Multi-view transformation network for 3d shape recognition.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Mvtn: Multi-view transformation network for 3d shape recognition

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.351117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation faf9ce29-ce5e-4ab1-b4f1-2fef47304470 · outbound

This paper cites Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:27:36.877884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6dbecb7a-20aa-46e5-8367-ed134d8c4b97 · outbound

This paper cites Denoising Diffusion Probabilistic Models.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Denoising Diffusion Probabilistic Models

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:27:36.891507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e7acc51b-0eb7-4133-b77c-cfd174f56f59 · outbound

This paper cites Pri3d: Can 3d priors help 2d representation learning? InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 5693–5702.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Pri3d: Can 3d priors help 2d representation learning? InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 5693–5702

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.309755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ac154d1c-187d-49da-8043-31e0454d3f21 · outbound

This paper cites A comprehensive survey on contrastive learning.Neurocomputing, 610:128645.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining A comprehensive survey on contrastive learning.Neurocomputing, 610:128645

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.346842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d9901db9-9d7a-4c63-971e-ae81051efcb5 · outbound

This paper cites An Embodied Generalist Agent in 3D World.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining An Embodied Generalist Agent in 3D World

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-17T14:22:18.773673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0e09e095-f0c7-4a87-b55e-dce7732c0ee7 · outbound

This paper cites Multi-view transformer for 3d visual grounding.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Multi-view transformer for 3d visual grounding

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.323054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 01779527-60e1-444e-8431-cc55ffcd04bc · outbound

This paper cites Frozen clip transformer is an efficient point cloud en- coder.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Frozen clip transformer is an efficient point cloud en- coder

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.344933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ff30f187-bf5b-4e2a-b0ea-69750a3f8f9d · outbound

This paper cites $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:27:36.858412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9fcef661-6cee-4053-86cb-95c8fc0cf59c · outbound

This paper cites Perceiver IO: A General Architecture for Structured Inputs & Outputs.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Perceiver IO: A General Architecture for Structured Inputs & Outputs

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:27:36.861655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 07cd58b7-0075-445c-a246-60115abcf57a · outbound

This paper cites Scaling up visual and vision-language representation learning with noisy text supervision.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Scaling up visual and vision-language representation learning with noisy text supervision

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.298227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation da2c2b08-b92b-44cb-a2d6-8f604e226792 · outbound

This paper cites Lift3d policy: Lifting 2d foundation models for robust 3d robotic ma- nipulation.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Lift3d policy: Lifting 2d foundation models for robust 3d robotic ma- nipulation

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.311327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 83154ea4-763d-4502-9e44-65bb88ef7b7c · outbound

This paper cites Kingma and Jimmy Ba.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Kingma and Jimmy Ba

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.315093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 537ba655-8893-47de-9a76-ce547efe1bb8 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Adam: A Method for Stochastic Optimization

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:27:36.848675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2ceeb50a-5650-4e02-bdaf-0c639d236712 · outbound

This paper cites Set transformer: A framework for attention-based permutation-invariant neural networks.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Set transformer: A framework for attention-based permutation-invariant neural networks

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.300542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ed489ff4-d5f6-46a5-acc4-4cbd2898241f · outbound

This paper cites Class: Contrastive learning via action se- quence supervision for robot manipulation.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Class: Contrastive learning via action se- quence supervision for robot manipulation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.321125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f829b1b5-d3d0-47a4-9e9e-68a15d8aca5a · outbound

This paper cites Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:27:36.845305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 51460893-ea02-45a6-9416-e83d77d2620e · outbound

This paper cites A multi-view projection-based object-aware graph network for dense captioning of point clouds.Computers & Graphics, 126:104156.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining A multi-view projection-based object-aware graph network for dense captioning of point clouds.Computers & Graphics, 126:104156

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.252049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 047c7a70-f8ac-4ff1-bda9-897b930213fa · outbound

This paper cites TIPS: Text-Image Pretraining with Spatial awareness.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining TIPS: Text-Image Pretraining with Spatial awareness

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:27:36.852460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 68c7a14d-b60a-468b-8be3-91b8be394917 · outbound

This paper cites GR00T N1: An Open Foundation Model for Generalist Humanoid Robots.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining GR00T N1: An Open Foundation Model for Generalist Humanoid Robots

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:27:36.855310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 430abd26-323b-43d4-a655-5e08b6cc22a8 · outbound

This paper cites Pointnet: Deep learning on point sets for 3d classification and segmentation.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Pointnet: Deep learning on point sets for 3d classification and segmentation

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.259955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 839f2c63-a781-42e8-a31a-6ec7dfa3db20 · outbound

This paper cites Pointnet++: Deep hierarchical feature learning on point sets in a metric space.Advances in neural information processing systems, 30.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Pointnet++: Deep hierarchical feature learning on point sets in a metric space.Advances in neural information processing systems, 30

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.353200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation afe5c7eb-34a4-47ce-9076-9eab5265b586 · outbound

This paper cites 3d-mvp: 3d multi- view pretraining for manipulation.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining 3d-mvp: 3d multi- view pretraining for manipulation

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.320043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9caa72a4-47e2-49ab-8433-7ae7b765a9d4 · outbound

This paper cites Learning transferable visual models from natural lan- guage supervision.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Learning transferable visual models from natural lan- guage supervision

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.271836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bede3e90-fb50-4272-89b2-b80325a74a0e · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.293364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ee44d256-fdd5-4292-9a30-5b5d2139851e · outbound

This paper cites Learning the RoPEs: Better 2D and 3D Position Encodings with STRING.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Learning the RoPEs: Better 2D and 3D Position Encodings with STRING

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:27:36.885411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1d2d14c6-82c8-4837-880e-83ff708feca9 · outbound

This paper cites Self-supervised visual descriptor learning for dense cor- respondence.IEEE Robotics and Automation Letters, 2 (2):420–427.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Self-supervised visual descriptor learning for dense cor- respondence.IEEE Robotics and Automation Letters, 2 (2):420–427

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.269530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6c8f155b-96a9-4714-8ada-96048da4f516 · outbound

This paper cites Perceiver-actor: A multi-task transformer for robotic ma- nipulation.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Perceiver-actor: A multi-task transformer for robotic ma- nipulation

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.280195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f17a7717-22af-45d5-9ee7-f604b22c5562 · outbound

This paper cites EVA-CLIP: Improved Training Techniques for CLIP at Scale.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining EVA-CLIP: Improved Training Techniques for CLIP at Scale

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:27:36.880704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a3d0d134-ca94-4058-a15c-0203fe0f537c · outbound

This paper cites Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:27:36.888636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 91d45c5e-cf4a-40c6-ac8f-ad55ccccae7f · outbound

This paper cites Mujoco: A physics engine for model-based control.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Mujoco: A physics engine for model-based control

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.316971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bdc581c5-b340-44df-adf1-e1fdf4af5568 · outbound

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

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Attention is all you need.Advances in neural information processing systems, 30

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.329087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2b6369f7-64d1-4cb9-acf8-81daf941fa6e · outbound

This paper cites Dynamic graph cnn for learning on point clouds.ACM Transac- tions on Graphics (tog), 38(5):1–12.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Dynamic graph cnn for learning on point clouds.ACM Transac- tions on Graphics (tog), 38(5):1–12

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.300344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4efc20a3-2ae3-405a-8504-20c163574875 · outbound

This paper cites ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulation.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulation

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:27:36.868328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9564fece-3e91-47a7-9ed4-d50a1a55a16b · outbound

This paper cites Point transformer v2: Grouped vector attention and partition-based pooling.Advances in Neu- ral Information Processing Systems, 35:33330–33342.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Point transformer v2: Grouped vector attention and partition-based pooling.Advances in Neu- ral Information Processing Systems, 35:33330–33342

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.272027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dadcd612-037c-46b7-b905-6e183ca0706f · outbound

This paper cites Point transformer v3: Simpler faster stronger.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Point transformer v3: Simpler faster stronger

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.335192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5b1a45c1-2f41-4ae9-a02e-5edb7aadeb9d · outbound

This paper cites Pointllm: Empowering large language models to understand point clouds.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Pointllm: Empowering large language models to understand point clouds

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.319028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1b797f68-fc98-4ca9-9f56-2c065b47e271 · outbound

This paper cites Ulip: Learning a unified representation of language, images, and point clouds for 3d understanding.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Ulip: Learning a unified representation of language, images, and point clouds for 3d understanding

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.341300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d6223955-d4bb-40a1-a3bd-3df6b9f2d4af · outbound

This paper cites Ulip-2: Towards scalable multimodal pre-training for 3d under- standing.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Ulip-2: Towards scalable multimodal pre-training for 3d under- standing

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.311923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0412ddcd-303b-4be0-b8ad-99c62cd14fd1 · outbound

This paper cites mt5: A massively multilingual pre-trained text-to- text transformer.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining mt5: A massively multilingual pre-trained text-to- text transformer

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.288796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 81c4f21a-03e5-4da7-ac7e-0cbcfa3a509a · outbound

This paper cites CoCa: Contrastive Captioners are Image-Text Foundation Models.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining CoCa: Contrastive Captioners are Image-Text Foundation Models

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:27:36.874628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 83e0764d-fcd2-4e59-8198-c9004deeb5c9 · outbound

This paper cites Point-bert: Pre-training 3d point cloud transformers with masked point modeling.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Point-bert: Pre-training 3d point cloud transformers with masked point modeling

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.286470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b6b04895-2c6a-4c50-93b5-db3ac162f866 · outbound

This paper cites Florence: A New Foundation Model for Computer Vision.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Florence: A New Foundation Model for Computer Vision

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-16T09:38:09.598269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1055e2f1-16d3-4d74-bf8f-f55a27ad9ae4 · outbound

This paper cites Zakka, Y.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Zakka, Y

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.262459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c265138a-7034-4176-ac32-fdab7a3660c2 · outbound

This paper cites Gnfactor: Multi-task real robot learning with generalizable neural feature fields.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Gnfactor: Multi-task real robot learning with generalizable neural feature fields

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.297944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation de0ca59c-5209-4938-98fd-7dbb30b5ee02 · outbound

This paper cites 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.296116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d075399b-e71e-48b7-8bb5-9d9814272f01 · outbound

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

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Sigmoid loss for language image pre- training

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.283053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation aaaab6e4-4841-407a-a800-5e8b18750999 · outbound

This paper cites Point- m2ae: multi-scale masked autoencoders for hierarchical point cloud pre-training.Advances in neural information processing systems, 35:27061–27074.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Point- m2ae: multi-scale masked autoencoders for hierarchical point cloud pre-training.Advances in neural information processing systems, 35:27061–27074

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.309370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e7b8d734-f51b-4dad-868b-37813d2d12c3 · outbound

This paper cites Pointclip: Point cloud understanding by clip.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Pointclip: Point cloud understanding by clip

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.348693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 37679273-1e9a-4aed-9842-c65850b31bec · outbound

This paper cites Point transformer.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Point transformer

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.265785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 240dbbd1-21ee-443c-a10b-8f49fcc8796f · outbound

This paper cites Zhao, Vikash Kumar, Sergey Levine, and Chelsea Finn.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Zhao, Vikash Kumar, Sergey Levine, and Chelsea Finn

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.337356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1306913b-d59c-460d-98df-8b5cf4445037 · outbound

This paper cites ALOHA Unleashed: A Simple Recipe for Robot Dexterity.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining ALOHA Unleashed: A Simple Recipe for Robot Dexterity

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:27:36.894779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2c0ae73b-0ed9-48cf-9a57-8d00a38fbc54 · outbound

This paper cites Uni3D: Exploring Unified 3D Representation at Scale.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Uni3D: Exploring Unified 3D Representation at Scale

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:27:36.901002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2236030c-0b3a-4e13-a079-1b2f3693d493 · outbound

This paper cites HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulation.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulation

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:27:36.871516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 75a99ab3-edf2-4b00-a637-e63254ad936d · outbound

This paper cites Pointclip v2: Prompting clip and gpt for pow- erful 3d open-world learning.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Pointclip v2: Prompting clip and gpt for pow- erful 3d open-world learning

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T08:30:46.326983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9e492f3f-2473-4608-bb71-4fef5b056a1d · outbound

This paper cites If the point cloud contains more than 0.3M points, we randomly subsample to 0.3M; otherwise, we pad with points at the origin (0,0,0) to reach 0.3M points.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining If the point cloud contains more than 0.3M points, we randomly subsample to 0.3M; otherwise, we pad with points at the origin (0,0,0) to reach 0.3M points

Reference 71

Resolution: malformed identifier; raw_fallback, observed 2026-05-16T08:30:46.277798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 63f85e20-4e0d-4abf-8ee1-8b102953c8b9 · outbound

This paper cites an unresolved cited work.

CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-05-16T08:30:46.333204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers