Paper Citation Record · LEDGER

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization

As of 19 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 2 inbound Pith citation observations for arXiv:2601.20317.

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

pith.paper-citation-record.v1
2601.20317 v2

Coverage vector

measured 65 of 65 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:45:32.833072Z

measured 67 of 67 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-25T06:37:17.739341Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-25T06:40:25.741118Z

Reference resolution

65 of 65 outbound references displayed

verified exact0
verified fuzzy33
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d9566443-67fe-4d5e-9fc2-414c07725408 · outbound

This paper cites Ahmed and K.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Ahmed and K

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.681580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7e73f657-59ba-48fb-82c2-cd182e2ffdc9 · outbound

This paper cites Quarot: Outlier-free 4-bit inference in rotated llms,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Quarot: Outlier-free 4-bit inference in rotated llms,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.580440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 267d241a-2bdf-489d-85e2-fdaf8163a72e · outbound

This paper cites Human-robot perception in industrial environments: A survey,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Human-robot perception in industrial environments: A survey,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.584873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf04073b-742f-4682-993e-2a34c86d1fb8 · outbound

This paper cites Diannao: a small-footprint high-throughput accelerator for ubiquitous machine-learning,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Diannao: a small-footprint high-throughput accelerator for ubiquitous machine-learning,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.653358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 42d4b62e-dd96-4f2e-9bcd-221004843b24 · outbound

This paper cites Eyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Eyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.640682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5966fd5a-fc49-431a-bfd4-983cd332db83 · outbound

This paper cites Bitmod: Bit-serial mixture-of- datatype llm acceleration,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Bitmod: Bit-serial mixture-of- datatype llm acceleration,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.627565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a1a71299-97e1-495f-88fc-c55ab890f811 · outbound

This paper cites Nvidia a100 gpu: Performance & innova- tion for gpu computing,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Nvidia a100 gpu: Performance & innova- tion for gpu computing,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.614962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 55601f20-e75d-4832-af3a-f047c52a1f49 · outbound

This paper cites Flashattention: Fast and memory-efficient exact attention with io-awareness,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Flashattention: Fast and memory-efficient exact attention with io-awareness,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.605626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4c2a18b-bb2c-4905-bd33-2a034915e6ee · outbound

This paper cites A systematic review of a digital twin city: A new pattern of urban governance toward smart cities,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization A systematic review of a digital twin city: A new pattern of urban governance toward smart cities,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.594317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 16d7ba38-a4f4-49c3-a806-6e0c896db6ae · outbound

This paper cites Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.613634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f5d5234-91b0-4531-982b-22616cfa5c78 · outbound

This paper cites Nvidia orin system-on-chip,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Nvidia orin system-on-chip,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.617776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6eea3f92-7780-4094-a258-c648467d6b6b · outbound

This paper cites Nvidia’s xavier soc,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Nvidia’s xavier soc,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.565583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation aa9fee53-0dbf-42d0-a70f-5582aae4a228 · outbound

This paper cites Quantized visual geometry grounded transformer,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Quantized visual geometry grounded transformer,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.625535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f440d782-e1b6-4294-b1bf-5f4e073426f5 · outbound

This paper cites Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.629287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00337676-8d6d-4197-882e-aa3a6ca9d900 · outbound

This paper cites Cicero: Addressing algorithmic and architectural bottlenecks in neural rendering by radiance warping and memory optimizations,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Cicero: Addressing algorithmic and architectural bottlenecks in neural rendering by radiance warping and memory optimizations,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.553216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b01ede58-b896-4f4b-8ebb-b0dfc82d8f89 · outbound

This paper cites Olive: Accelerating large language models via hardware- friendly outlier-victim pair quantization,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Olive: Accelerating large language models via hardware- friendly outlier-victim pair quantization,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.637432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c66b8ec-81b8-4538-8a90-4047b4e66c85 · outbound

This paper cites Eie: Efficient inference engine on compressed deep neural network,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Eie: Efficient inference engine on compressed deep neural network,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.532227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6eabd7b6-c737-4e29-bf37-66cf25396694 · outbound

This paper cites Hartley and A.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Hartley and A

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.645457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5645d37-a2c4-4e32-bee3-762ab21c7eb9 · outbound

This paper cites ITU-T Recommendation H.265: High Efficiency Video Coding,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization ITU-T Recommendation H.265: High Efficiency Video Coding,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.510431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3d395439-53bd-431e-acee-2fd7cd5e5a41 · outbound

This paper cites JESD209-4: Low Power Double Data Rate 4 (LPDDR4),.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization JESD209-4: Low Power Double Data Rate 4 (LPDDR4),

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.497878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d0d387da-6c8b-4693-95e8-0784c52cac48 · outbound

This paper cites JESD235D: High Bandwidth Memory (HBM) DRAM,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization JESD235D: High Bandwidth Memory (HBM) DRAM,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.484807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 80a5150c-30fb-4b18-a29c-f42357d7cbc0 · outbound

This paper cites JESD209-5C: Low Power Double Data Rate (LPDDR5/5X),.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization JESD209-5C: Low Power Double Data Rate (LPDDR5/5X),

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.471803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e2230dad-3405-4061-9e91-70241facfeed · outbound

This paper cites JESD238B.01: High Bandwidth Memory (HBM3) DRAM,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization JESD238B.01: High Bandwidth Memory (HBM3) DRAM,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.459086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6c632e37-5655-4a80-a4a5-4c3c10873bf8 · outbound

This paper cites Large scale multi-view stereopsis evaluation,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Large scale multi-view stereopsis evaluation,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.668988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acc11e87-73b7-4bbe-a08e-60b86c0da6a8 · outbound

This paper cites Stripes: Bit-serial deep neural network computing,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Stripes: Bit-serial deep neural network computing,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.437934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bc874e3d-b3c7-4072-b7df-75e4ffdc5e44 · outbound

This paper cites 3d gaussian splatting for real-time radiance field rendering.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization 3d gaussian splatting for real-time radiance field rendering

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.676880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b47ce9a9-084b-4ff8-8286-0c5873f40c79 · outbound

This paper cites The discrete cosine transform (dct): theory and appli- cation,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization The discrete cosine transform (dct): theory and appli- cation,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.416489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 13fbe69b-ba43-482a-9e12-ff58996c102b · outbound

This paper cites Tender: Accelerating large language models via tensor decomposition and runtime requantization,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Tender: Accelerating large language models via tensor decomposition and runtime requantization,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.402466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5dbb3fd4-c5cd-4c67-913c-8f160d82900e · outbound

This paper cites Neurex: A case for neural rendering acceleration,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Neurex: A case for neural rendering acceleration,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.389073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dac74b6f-f74d-4d8b-abda-16fd3d000f9e · outbound

This paper cites Gscore: Efficient radiance field rendering via architectural support for 3d gaussian splatting,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Gscore: Efficient radiance field rendering via architectural support for 3d gaussian splatting,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.376052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation df5ddf42-008f-4bea-836c-f6885c111137 · outbound

This paper cites Rt-nerf: Real-time on-device neural radiance fields towards immersive ar/vr rendering,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Rt-nerf: Real-time on-device neural radiance fields towards immersive ar/vr rendering,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.362517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ba642f00-e4b8-4799-a651-5dfc87e19ffe · outbound

This paper cites Mbq: Modality-balanced quantization for large vision- language models,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Mbq: Modality-balanced quantization for large vision- language models,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.348431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5c79ee49-8cef-481a-83d8-1eff93903f17 · outbound

This paper cites Instant-3d: Instant neural radiance field training towards on-device ar/vr 3d reconstruction,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Instant-3d: Instant neural radiance field training towards on-device ar/vr 3d reconstruction,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.705047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dee5c653-b400-469f-aaa8-9d30b76f1bbe · outbound

This paper cites Awq: Activation-aware weight quanti- zation for on-device llm compression and acceleration,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Awq: Activation-aware weight quanti- zation for on-device llm compression and acceleration,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.708695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c1e28ac-2635-4b63-938f-7be38c50282b · outbound

This paper cites Metasapiens: Real-time neural rendering with efficiency-aware pruning and accelerated foveated rendering,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Metasapiens: Real-time neural rendering with efficiency-aware pruning and accelerated foveated rendering,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.712830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a547c197-2e3e-418f-af21-b958cce92107 · outbound

This paper cites Flightvgm: Efficient video generation model inference with online sparsification and hybrid precision on fpgas,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Flightvgm: Efficient video generation model inference with online sparsification and hybrid precision on fpgas,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.716795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43f6489c-dcde-47a8-9e5c-6162faa2f3f2 · outbound

This paper cites HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.720879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0f7cc0b-eef1-4d65-b2aa-3d7b5016aac8 · outbound

This paper cites SpinQuant: LLM quantization with learned rotations.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization SpinQuant: LLM quantization with learned rotations

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.725102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d4eb6f0-1f83-45cf-b77c-acf98818dea9 · outbound

This paper cites Fast inverse square root,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Fast inverse square root,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.301666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ddc2eb2f-503e-4827-b785-7dc8caa8330b · outbound

This paper cites Ramulator 2.0: A modern, modular, and extensible dram simulator,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Ramulator 2.0: A modern, modular, and extensible dram simulator,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.733446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 412926dd-438e-4f47-8076-2e339a7fc95f · outbound

This paper cites Digital twins: A survey on enabling technologies, challenges, trends and future prospects,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Digital twins: A survey on enabling technologies, challenges, trends and future prospects,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.280601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 778742eb-22f4-4271-90f0-3e8f4db9e503 · outbound

This paper cites Nerf: Representing scenes as neural radiance fields for view synthesis,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Nerf: Representing scenes as neural radiance fields for view synthesis,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.741435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ca4beda-470e-49f3-9413-23ce64652a5a · outbound

This paper cites Response time in man-computer conversational transac- tions,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Response time in man-computer conversational transac- tions,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.259467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 146a7205-ca95-4348-927b-53175999931e · outbound

This paper cites Instant neural graphics primitives with a multiresolution hash encoding,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Instant neural graphics primitives with a multiresolution hash encoding,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.749692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed7be072-7359-431c-8243-50057bb2b881 · outbound

This paper cites A study on tolerable waiting time: how long are web users willing to wait?.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization A study on tolerable waiting time: how long are web users willing to wait?

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.238106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation af42ee64-01a1-4472-b575-bc755cc53b7d · outbound

This paper cites Dinov2: Learning robust visual features without supervision,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Dinov2: Learning robust visual features without supervision,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.224944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b94c3c1a-a832-49b4-9491-5b7ff15ce69a · outbound

This paper cites Pytorch: An imperative style, high-performance deep learning library,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Pytorch: An imperative style, high-performance deep learning library,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.761822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85241db1-cfde-4232-b86f-1d8f56c0a3a5 · outbound

This paper cites Hadamard transform image coding,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Hadamard transform image coding,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.765746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 476112a2-ac13-4c1d-b0fd-6dc442a7eeab · outbound

This paper cites Common objects in 3d: Large-scale learning and evaluation of real-life 3d category reconstruction,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Common objects in 3d: Large-scale learning and evaluation of real-life 3d category reconstruction,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.769514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bda3f11b-e525-4294-9109-d38d7b79e676 · outbound

This paper cites Structure-from-motion revisited,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Structure-from-motion revisited,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.773349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b193f0a8-f7a9-4797-8540-a366584bbb79 · outbound

This paper cites Bit fusion: Bit-level dynamically composable architecture for accelerating deep neural network,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Bit fusion: Bit-level dynamically composable architecture for accelerating deep neural network,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.179513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 555a70de-4b81-495e-b9a2-bb01b9a74210 · outbound

This paper cites Scene coordinate regression forests for camera relocalization in rgb-d images,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Scene coordinate regression forests for camera relocalization in rgb-d images,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.781561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efa12d83-9473-45f8-a233-36a533b5908f · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.785379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e535b9b4-fc0d-45ed-b93e-4299509bb3ba · outbound

This paper cites QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.789339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa041710-06c0-433f-84ee-b736163dcbb5 · outbound

This paper cites Vggt: Visual geometry grounded transformer,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Vggt: Visual geometry grounded transformer,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.793718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d14d636-99e1-4493-9e81-968268a7ccf7 · outbound

This paper cites Tataa: Programmable mixed-precision transformer acceleration with a trans- formable arithmetic architecture,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Tataa: Programmable mixed-precision transformer acceleration with a trans- formable arithmetic architecture,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.149793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f91c5a19-130f-4b66-803e-49ef378ba645 · outbound

This paper cites Smoothquant: Accurate and efficient post-training quantization for large language models,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Smoothquant: Accurate and efficient post-training quantization for large language models,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.801406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ec84763-9cd3-4673-9e67-ef933549f359 · outbound

This paper cites Llm. 265: Video codecs are secretly tensor codecs,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Llm. 265: Video codecs are secretly tensor codecs,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.128206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8166114a-0387-415f-a9b1-133a4b891c8d · outbound

This paper cites Advances in feed-forward 3d reconstruction and view synthesis: A survey,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Advances in feed-forward 3d reconstruction and view synthesis: A survey,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.809301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46125bf7-8e08-4c83-9442-a6cb60e675dc · outbound

This paper cites D ´eja view: Spatio-temporal compute reuse for ‘energy-efficient 360 vr video streaming,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization D ´eja view: Spatio-temporal compute reuse for ‘energy-efficient 360 vr video streaming,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.114954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6f473e6f-09e5-4ac3-82e4-2c93f6d9acb0 · outbound

This paper cites ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.817148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0164de82-b347-4396-9087-0d09bb068d9c · outbound

This paper cites Mixdq: Memory-efficient few-step text-to-image diffu- sion models with metric-decoupled mixed precision quantization,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Mixdq: Memory-efficient few-step text-to-image diffu- sion models with metric-decoupled mixed precision quantization,

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.101400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 851e66c4-06bf-4d3d-892f-98bf294b2bec · outbound

This paper cites Unsupervised learning of depth and ego-motion from video,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Unsupervised learning of depth and ego-motion from video,

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-15T15:45:32.825204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f716a2de-8f06-44c2-9eb2-c099791703b7 · outbound

This paper cites Megascale-infer: Efficient mixture- of-experts model serving with disaggregated expert parallelism,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Megascale-infer: Efficient mixture- of-experts model serving with disaggregated expert parallelism,

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.080482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0f7a4383-2052-4763-a000-8fb0097b4dab · outbound

This paper cites Nice-slam: Neural implicit scalable encoding for slam,.

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization Nice-slam: Neural implicit scalable encoding for slam,

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:45:33.066519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation 44736ec8-7042-49bf-8d96-fe8c63dcecec · inbound

Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer cites this paper.

Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-16T01:21:44.535478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b54b4f26-a010-49f8-9268-b5f6662fa145 · inbound

Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer cites this paper.

Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-16T01:21:44.535478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.