pith. machine review for the scientific record. sign in

arxiv: 2605.00548 · v2 · submitted 2026-05-01 · 💻 cs.CV · cs.GR

Recognition: no theorem link

Colorful-Noise: Training-Free Low-Frequency Noise Manipulation for Color-Based Conditional Image Generation

Nadav Z. Cohen , Ofir Abramovich , Ariel Shamir
Authors on Pith no claims yet

Pith reviewed 2026-05-12 02:14 UTC · model grok-4.3

classification 💻 cs.CV cs.GR
keywords diffusion modelsnoise manipulationlow-frequencyimage generationcolor conditioningtraining-freefrequency analysis
0
0 comments X

The pith

Low-frequency components of the input noise set global structure and color in diffusion-generated images, allowing training-free conditioning via simple prior-based edits.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Text-to-image diffusion models begin with white Gaussian noise and gradually denoise it into a picture. Although every frequency band in that noise carries roughly equal energy, the low-frequency parts turn out to be the main carriers of overall layout and color palette, while higher frequencies supply only the fine texture. The paper shows that editing just the low-frequency slice of the noise with a matching low-frequency prior taken from a reference image is enough to steer the final output toward those colors and shapes. High-frequency content remains untouched and therefore supplies natural detail variation across samples. The result is a lightweight, training-free procedure that adds controllable color and structure guidance to any existing diffusion model.

Core claim

Although all frequencies in white Gaussian noise have comparable statistical energy, low-frequency components primarily determine the image's global structure and color composition, while high-frequency components control finer details. Simple manipulations of the low-frequency noise using low-frequency image priors can therefore condition the generation process to reconstruct those low-frequency visual cues, steering overall appearance while leaving high-frequency components free to produce varied fine details.

What carries the argument

Low-frequency noise manipulation with low-frequency image priors, which isolates the structural and chromatic information in the initial noise and replaces it with a matching prior before the diffusion process begins.

If this is right

  • Overall image structure and color can be steered without retraining or modifying the diffusion model.
  • High-frequency noise continues to generate diverse fine details, preserving output variability.
  • The approach adds minimal computational overhead and works as a plug-in step on existing text-to-image pipelines.
  • Specific visual attributes such as color composition become more predictable from the initial noise alone.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same frequency separation might be used to control other mid-level attributes by targeting different bands of the noise spectrum.
  • Prompt engineering for color consistency could be partly replaced by this noise-level intervention.
  • The method's effectiveness on non-photographic domains such as illustrations or abstract art remains to be checked.

Load-bearing premise

Low-frequency noise components are the dominant drivers of global structure and color, and editing them conditions the output without creating unwanted side effects or interactions with higher frequencies.

What would settle it

Running the diffusion process after low-frequency noise edits and finding that the generated images show no consistent change in global color distribution or coarse layout compared with unedited noise.

Figures

Figures reproduced from arXiv: 2605.00548 by Ariel Shamir, Nadav Z. Cohen, Ofir Abramovich.

Figure 1
Figure 1. Figure 1: Colorful-Noise. Conditioning the low-frequency components of white Gaussian noise with structured color maps enables control over both image structure and color scheme, without requiring training or incurring any additional computational overhead (our method works in latent space but examples shown here are in pixel space for illustrative purposes). Text-to-image diffusion models generate images by gradual… view at source ↗
Figure 2
Figure 2. Figure 2: Method Overview. Colorful-Noise simply replaces the low fre￾quency components of the white Gaussian noise with the low frequency of some conditioning reference image in latent space (in this case, a color stencil). Although the resulting noise is biased (i.e. not “white”), it can still be used to successfully generate a high-quality image, while conditioning the desired results (note that the visualization… view at source ↗
Figure 3
Figure 3. Figure 3: Frequency Mixing in Noise Latents. We decompose Gaussian noise latents into low, mid, and high frequency bands and recombine them to generate images from a fixed prompt (“A photo of a colorful bird”). Rows share the same low frequencies, columns share the same high frequencies, and two mid-frequency variations are shown per pair. As can be observed, low frequencies dominate global structure and color, mid … view at source ↗
Figure 4
Figure 4. Figure 4: Noise and Image Combinations. We generate images by mixing noise with the low-frequency components of natural images. As observed, replacing low frequencies allows for a surprising reconstruction of the refer￾ence image’s low-frequency content—even without a prompt—when appro￾priately scaled. (Zoom in for a better view.) results of this experiment are shown in [PITH_FULL_IMAGE:figures/full_fig_p004_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: 𝛼 and 𝛾 Ablation Study. We ablate the low-frequency ratio 𝛼 and scale 𝛾 using synthetic low-frequency inputs. (A) Conditional inputs. (B) PSD-based whiteness shows that smaller 𝛼 and 𝛾 better preserve spectral balance. (C) Promptless generation indicates that large 𝛼 or 𝛾 introduce color and structural artifacts, while smaller values preserve low-frequency color. (D) With text conditioning, high 𝛼 overcons… view at source ↗
Figure 6
Figure 6. Figure 6: Localizing Colorful-Sketch Conditioning. On the left we demonstrate how a single masked condition can generate color/structure aligned results for various prompts. The top row shows four simple masked scribble conditions (the black background is masked out) and the four corresponding results for various prompts. The middle and bottom rows show two simple masked sketch conditioning various prompts. On the r… view at source ↗
Figure 7
Figure 7. Figure 7 [PITH_FULL_IMAGE:figures/full_fig_p006_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Color-Based Style Alignment. Results for Color-Based style alignment using SDXL. Bottom reference © Augustin Arroyo (@flowalistic on Instagram). All rights reserved. large Conditioning Scale (𝛾) small large Conditioning Scale (𝛾) small “A portrait of a woman with colorful lighting” “A jumping leopard sticker” “A photo of a cat walking in the city” “Three Siamese fighting fish in the sea” “An Elephant and a… view at source ↗
Figure 9
Figure 9. Figure 9: Colorful-Noise with Flux: results of various applications using Flux Flow-based model. Color-Preserving Stylization. By design, Colorful-Noise condi￾tions the output using low-frequency information from a reference image. This allows combining it with methods for high-frequency control. We show results of using Colorful-Noise alongside Control￾Net [Zhang et al. 2023a] to guide fine details with a Canny map… view at source ↗
Figure 10
Figure 10. Figure 10: Color-Preserving Stylization. Combining low-frequency conditioning of Colorful-Noise with high-frequency conditioning of structure and style conditioning. See text for detailed explanation. Prompts: "Colorful buildings" (Top), "Two Macaws" (Bottom). Color Style Interpolation Style Reference Colorful-Noise Reference ControlNet Reference [PITH_FULL_IMAGE:figures/full_fig_p008_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Color-Style Interpolation. Color-Style Interpolation. Colorful noise can be partially applied via linear interpolation with white noise. Combined with style and Canny conditioning, this produces a smooth transition between the colors of a reference image (right) and a style image (left), while preserving other aspects of the style reference. Prompts: "A portrait of a man" (Top), "A frog on a branch" (Bott… view at source ↗
Figure 12
Figure 12. Figure 12: Prompt Ablation Study. We investigate the effect of various prompt levels on the output, when conditioned with a photo, a full colorful￾sketch, and a masked colorful-sketch. As there is no semantic matching between colors and subject in the prompt, the generation model is free to interpret the color mapping freely which leads to various semantic in￾terpretations based on the input prompt. See higher resol… view at source ↗
Figure 13
Figure 13. Figure 13: Noise and Image Combinations. Images generated using noise injected with Mid-Frequencies cause the diffusion process to collapse and images generated using noise injected with High-Frequencies show minimal impact on the output, apparent by the similarity of the result to the unbiased output [PITH_FULL_IMAGE:figures/full_fig_p012_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Frequency Mixing in Noise Latents. Additional example and full t-SNE plots with labels for low-, mid-, and high-frequencies. low-frequency components. Additional examples from the dataset are provided in [PITH_FULL_IMAGE:figures/full_fig_p013_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: Color Evaluation Set. A small set of examples from the colorful evaluation dataset, highlighting its variability. which controls the level of decomposition, where for 𝐽 = 𝑖 the func￾tion runs recursively on the previous low level frequencies 𝐿𝐿(𝑖−1) , where 𝐿𝐿0 is the input image. Formally: Let W be a wavelet func￾tion, then for an input Image 𝐼 and decomposition level 𝐽 = 𝑖 > 0 we have: (𝐿𝐿, 𝐿𝐻, 𝐻𝐿, 𝐻𝐻)𝑖… view at source ↗
Figure 16
Figure 16. Figure 16: Wavelet Colorful-Sketch Conditioning Results. Results of applying colorful noise using wavelets for frequency decomposition. We present results with identical conditional inputs to enable direct comparison. signals can replace white noise in the low-frequency components. Unlike Huang et al., we extract low-frequency components from images to explicitly condition the output on specific structures. Mo￾tivat… view at source ↗
Figure 17
Figure 17. Figure 17: Colorful Noise for Blue-Noise Diffusion. We evaluate blue-noise inputs with SDXL (top) and a blue-noise–trained model from Huang et al. (bottom). For both, we compare blue-noise generation with and without colorful-noise conditioning. Interpolating from white to blue noise in SDXL, as proposed by Huang et al., leads to degraded results; however, adding colorful-noise conditioning improves outputs compared… view at source ↗
Figure 18
Figure 18. Figure 18: Qualitative Comparison to Previous Works. ColorfulNoise supports multiple tasks, including Image Variation generation, Colorfield-to-Image synthesis and Image Color Transfer. Shown are representative results on the Aesthetic-4K evaluation set. 17 [PITH_FULL_IMAGE:figures/full_fig_p017_18.png] view at source ↗
Figure 19
Figure 19. Figure 19: Prompt Ablation Study. We investigate the effect of various prompt levels on the output, when conditioned with a photo, a full colorful-sketch, and a masked colorful-sketch. As there is no semantic matching between colors and subject in the prompt, the generation model is free to interpret the color mapping freely which leads to various semantic interpretations based on the input prompt. The effects of gu… view at source ↗
Figure 20
Figure 20. Figure 20: Additional Results. Additional results for Color-Based Style Alignment with SDXL. 19 [PITH_FULL_IMAGE:figures/full_fig_p019_20.png] view at source ↗
Figure 21
Figure 21. Figure 21: Wavelets Color-Based Style Alignment Results. Results of applying colorful noise via wavelet-based frequency decomposition. All results use the same conditional inputs to enable direct comparison. Bottom reference © Augustin Arroyo (@flowalistic on Instagram). All rights reserved. 20 [PITH_FULL_IMAGE:figures/full_fig_p020_21.png] view at source ↗
Figure 22
Figure 22. Figure 22: Additional Results. Additional results illustrating variations induced by changes in the 𝛾 scale-factor. 21 [PITH_FULL_IMAGE:figures/full_fig_p021_22.png] view at source ↗
Figure 23
Figure 23. Figure 23: Additional Results. Additional results illustrating variations induced by changes in the random seed. 22 [PITH_FULL_IMAGE:figures/full_fig_p022_23.png] view at source ↗
Figure 24
Figure 24. Figure 24: Additional Results. Additional results for masked-sketches (Top 4 rows) and full-sketches (last row). 23 [PITH_FULL_IMAGE:figures/full_fig_p023_24.png] view at source ↗
Figure 25
Figure 25. Figure 25: Additional Results. Additional results for Color-Preserving Stylization. 24 [PITH_FULL_IMAGE:figures/full_fig_p024_25.png] view at source ↗
Figure 26
Figure 26. Figure 26: High-Resolution Results. High resolution results from [PITH_FULL_IMAGE:figures/full_fig_p025_26.png] view at source ↗
Figure 27
Figure 27. Figure 27: High-Resolution Results. High resolution results from [PITH_FULL_IMAGE:figures/full_fig_p026_27.png] view at source ↗
Figure 28
Figure 28. Figure 28: High-Resolution Results. High resolution results from [PITH_FULL_IMAGE:figures/full_fig_p027_28.png] view at source ↗
Figure 29
Figure 29. Figure 29: High-Resolution Results. High resolution results from [PITH_FULL_IMAGE:figures/full_fig_p028_29.png] view at source ↗
read the original abstract

Text-to-image diffusion models generate images by gradually converting white Gaussian noise into a natural image. White Gaussian noise is well suited for producing diverse outputs from a single text prompt due to its absence of structure. However, this very property limits control over, and predictability of, specific visual attributes, as the noise is not human-interpretable. In this work, we investigate the characteristics of the input noise in diffusion models. We show that, although all frequencies in white Gaussian noise have comparable statistical energy, low-frequency components primarily determine the images global structure and color composition, while high-frequency components control finer details. Building on this observation, we demonstrate that simple manipulations of the low-frequency noise using low-frequency image priors can effectively condition the generation process to reconstruct these low-frequency visual cues. This allows us to define a simple, training-free method with minimal overhead that steers overall image structure and color, while letting high-frequency components freely emerge as fine details, enabling variability across generated outputs.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper claims that in text-to-image diffusion models, although all frequencies in the initial white Gaussian noise have comparable energy, the low-frequency components predominantly determine the global structure and color composition of the generated image x_0, while high-frequency components control finer details. Building on this, it proposes a simple training-free method that manipulates the low-frequency part of the noise x_T using low-frequency priors extracted from reference images (via FFT or similar) to steer overall color and structure, while allowing high-frequency noise to produce variable details.

Significance. If the frequency-separation claim holds and the manipulations propagate reliably through the reverse diffusion process, the method would provide an efficient, training-free mechanism for color-based conditioning in diffusion models. This could be valuable for applications needing controllable global attributes without retraining or heavy compute, while preserving output diversity. The approach is lightweight and interpretable, which is a strength if empirically validated.

major comments (3)
  1. [§3] §3 (Empirical Observation): The central claim that low-frequency noise components primarily determine global structure and color (while high-freq control details) is presented as an observation but lacks quantitative validation such as frequency-domain correlation metrics or ablation studies comparing power spectra of x_T components to those of x_0 across multiple timesteps and models. Without this, it is unclear whether the separation is robust or model-specific.
  2. [§4] §4 (Method and Propagation): The proposed low-frequency manipulation (e.g., replacement or blending of FFT coefficients in x_T using image priors) assumes that these edits survive the U-Net's downsampling, upsampling, skip connections, and attention layers without significant mixing or dilution across frequency bands. No analysis, frequency decomposition of intermediate activations, or ablation on output spectra is provided to confirm that low-freq control remains localized to color/structure rather than introducing artifacts or being overridden.
  3. [Evaluation] Evaluation section: The abstract and method description mention 'effectively condition the generation' but the manuscript provides no standard metrics (e.g., color histogram distance, LPIPS for structure, FID for quality, or user studies) comparing the proposed method against baselines like prompt engineering or ControlNet-style conditioning. This makes it impossible to assess whether the claimed variability in details is preserved or if unintended side effects occur.
minor comments (2)
  1. [§4] The notation for the low-frequency prior extraction (e.g., how the cutoff frequency is chosen or how the prior image is processed) is introduced without a clear equation or pseudocode, making the method harder to reproduce.
  2. Figure captions and the abstract use 'low-frequency image priors' without specifying whether these are derived from the target image, a reference, or a color palette, which could confuse readers.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback on our manuscript. We address each major comment point by point below, indicating where revisions will be made to strengthen the paper.

read point-by-point responses

  1. Referee: [§3] The central claim that low-frequency noise components primarily determine global structure and color (while high-freq control details) is presented as an observation but lacks quantitative validation such as frequency-domain correlation metrics or ablation studies comparing power spectra of x_T components to those of x_0 across multiple timesteps and models. Without this, it is unclear whether the separation is robust or model-specific.

    Authors: We acknowledge that §3 currently relies primarily on qualitative visualizations and illustrative examples to support the frequency-separation observation. To address this, we will add quantitative validation in the revised manuscript, including Pearson correlation metrics between low-frequency FFT components of x_T and x_0, as well as power-spectrum ablation plots across multiple timesteps and diffusion models (e.g., Stable Diffusion variants). These additions will demonstrate the robustness of the claim beyond the current examples. revision: yes

  2. Referee: [§4] The proposed low-frequency manipulation (e.g., replacement or blending of FFT coefficients in x_T using image priors) assumes that these edits survive the U-Net's downsampling, upsampling, skip connections, and attention layers without significant mixing or dilution across frequency bands. No analysis, frequency decomposition of intermediate activations, or ablation on output spectra is provided to confirm that low-freq control remains localized to color/structure rather than introducing artifacts or being overridden.

    Authors: We agree that explicit propagation analysis is missing. In the revision, we will include frequency-domain decomposition of intermediate U-Net activations (at downsampling, upsampling, and attention layers) for selected examples, showing that low-frequency edits remain largely localized. We will also add output-spectrum ablations demonstrating that high-frequency variability is preserved and that artifacts are minimal when the manipulation strength is controlled. revision: yes

  3. Referee: [Evaluation] The abstract and method description mention 'effectively condition the generation' but the manuscript provides no standard metrics (e.g., color histogram distance, LPIPS for structure, FID for quality, or user studies) comparing the proposed method against baselines like prompt engineering or ControlNet-style conditioning. This makes it impossible to assess whether the claimed variability in details is preserved or if unintended side effects occur.

    Authors: We recognize the value of quantitative evaluation. The revised evaluation section will report color histogram distances to the reference priors (for color control), LPIPS between generated images and low-frequency priors (for structure), and FID scores to quantify quality and diversity relative to unconditioned sampling. We will also include comparisons against prompt-engineering baselines. Direct comparison to trained methods such as ControlNet will be framed as complementary, highlighting the training-free advantage while noting differences in control granularity. revision: yes

Circularity Check

0 steps flagged

No circularity; central claim rests on empirical observation of noise frequencies, not self-referential derivation

full rationale

The paper states an observation that low-frequency components of white Gaussian noise primarily determine global structure and color while high-frequency components control details, then builds a training-free manipulation method on this. This is presented as an empirical finding demonstrated via experiments rather than any mathematical derivation, equation, or fitted parameter that reduces the result to its own inputs by construction. No self-citations, ansatzes, or uniqueness theorems are invoked in the provided text to load-bear the claim. The method is self-contained as a direct manipulation of input noise x_T, with no reduction of predictions to prior fits or definitions.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the unproven observation that low-frequency noise determines global structure and color; no free parameters or invented entities are mentioned.

axioms (1)
  • domain assumption Low-frequency components of white Gaussian noise primarily determine global structure and color composition in generated images
    This is the key observation stated in the abstract upon which the method is built.

pith-pipeline@v0.9.0 · 5475 in / 1103 out tokens · 40442 ms · 2026-05-12T02:14:10.183253+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

144 extracted references · 144 canonical work pages · 2 internal anchors

  1. [1]

    Abril and Robert Plant

    Patricia S. Abril and Robert Plant. The patent holder's dilemma: Buy, sell, or troll?. Communications of the ACM. 2007. doi:10.1145/1188913.1188915

    work page doi:10.1145/1188913.1188915 2007

  2. [2]

    Deciding equivalances among conjunctive aggregate queries

    Sarah Cohen and Werner Nutt and Yehoshua Sagic. Deciding equivalances among conjunctive aggregate queries. 2007. doi:10.1145/1219092.1219093

    work page doi:10.1145/1219092.1219093 2007

  3. [3]

    Special issue: Digital Libraries. 1996

    work page 1996

  4. [4]

    Understanding Policy-Based Networking

    David Kosiur. Understanding Policy-Based Networking. 2001

    work page 2001

  5. [7]

    The title of book two. 2008. doi:10.1007/3-540-09237-4

    work page doi:10.1007/3-540-09237-4 2008

  6. [8]

    Asad Z. Spector. Achieving application requirements. Distributed Systems. 1990. doi:10.1145/90417.90738

    work page doi:10.1145/90417.90738 1990

  7. [9]

    Douglass and David Harel and Mark B

    Bruce P. Douglass and David Harel and Mark B. Trakhtenbrot. Statecarts in use: structured analysis and object-orientation. Lectures on Embedded Systems. 1998. doi:10.1007/3-540-65193-4_29

    work page doi:10.1007/3-540-65193-4_29 1998

  8. [10]

    Donald E. Knuth. The Art of Computer Programming, Vol. 1: Fundamental Algorithms (3rd. ed.). 1997

    work page 1997

  9. [11]

    Donald E. Knuth. The Art of Computer Programming. 1998

    work page 1998

  10. [12]

    Structured Variational Inference Procedures and their Realizations (as incol)

    Dan Geiger and Christopher Meek. Structured Variational Inference Procedures and their Realizations (as incol). Proceedings of Tenth International Workshop on Artificial Intelligence and Statistics, The Barbados

    work page

  11. [13]

    Stan W. Smith. An experiment in bibliographic mark-up: Parsing metadata for XML export. Proceedings of the 3rd. annual workshop on Librarians and Computers. 2010. doi:99.9999/woot07-S422

    work page 2010

  12. [14]

    Catch me, if you can: Evading network signatures with web-based polymorphic worms

    Matthew Van Gundy and Davide Balzarotti and Giovanni Vigna. Catch me, if you can: Evading network signatures with web-based polymorphic worms. Proceedings of the first USENIX workshop on Offensive Technologies. 2007

    work page 2007

  13. [15]

    Catch me, if you can: Evading network signatures with web-based polymorphic worms

    Matthew Van Gundy and Davide Balzarotti and Giovanni Vigna. Catch me, if you can: Evading network signatures with web-based polymorphic worms. Proceedings of the first USENIX workshop on Offensive Technologies. 2008

    work page 2008

  14. [16]

    Catch me, if you can: Evading network signatures with web-based polymorphic worms

    Matthew Van Gundy and Davide Balzarotti and Giovanni Vigna. Catch me, if you can: Evading network signatures with web-based polymorphic worms. Proceedings of the first USENIX workshop on Offensive Technologies. 2009

    work page 2009

  15. [17]

    Predicate Path expressions

    Sten Andler. Predicate Path expressions. Proceedings of the 6th. ACM SIGACT-SIGPLAN symposium on Principles of Programming Languages. 1979. doi:10.1145/567752.567774

    work page doi:10.1145/567752.567774 1979

  16. [18]

    LOGICS of Programs: AXIOMATICS and DESCRIPTIVE POWER

    David Harel. LOGICS of Programs: AXIOMATICS and DESCRIPTIVE POWER. 1978

    work page 1978

  17. [19]

    Anisi , title =

    David A. Anisi , title =

    work page

  18. [20]

    Clarkson

    Kenneth L. Clarkson. Algorithms for Closest-Point Problems (Computational Geometry). 1985

    work page 1985

  19. [21]

    Introduction to Bayesian Statistics

    Harry Thornburg. Introduction to Bayesian Statistics. 2001

    work page 2001

  20. [22]

    CLIFFORD: a Maple 11 Package for Clifford Algebra Computations, version 11

    Rafal Ablamowicz and Bertfried Fauser. CLIFFORD: a Maple 11 Package for Clifford Algebra Computations, version 11. 2007

    work page 2007

  21. [23]

    Stats and Analysis

    Poker-Edge.Com. Stats and Analysis. 2006

    work page 2006

  22. [24]

    A more perfect union

    Barack Obama. A more perfect union. 2008

    work page 2008

  23. [25]

    The fountain of youth

    Joseph Scientist. The fountain of youth. 2009

    work page 2009

  24. [26]

    Solder man

    Dave Novak. Solder man. ACM SIGGRAPH 2003 Video Review on Animation theater Program: Part I - Vol. 145 (July 27--27, 2003). 2003. doi:99.9999/woot07-S422

    work page 2003

  25. [27]

    Interview with Bill Kinder: January 13, 2005

    Newton Lee. Interview with Bill Kinder: January 13, 2005. Comput. Entertain. 2005. doi:10.1145/1057270.1057278

    work page doi:10.1145/1057270.1057278 2005

  26. [28]

    The Enabling of Digital Libraries

    Bernard Rous. The Enabling of Digital Libraries. Digital Libraries. 2008

    work page 2008

  27. [30]

    (new) Finding minimum congestion spanning trees , journal =

    Werneck, Renato and Setubal, Jo\. (new) Finding minimum congestion spanning trees , journal =. 2000 , issn =. doi:10.1145/351827.384253 , acmid =

    work page doi:10.1145/351827.384253 2000

  28. [32]

    and Mei, Alessandro , title =

    Conti, Mauro and Di Pietro, Roberto and Mancini, Luigi V. and Mei, Alessandro , title =. Inf. Fusion , volume =. 2009 , issn =. doi:10.1016/j.inffus.2009.01.002 , acmid =

    work page doi:10.1016/j.inffus.2009.01.002 2009

  29. [33]

    and Hutchful, David K

    Li, Cheng-Lun and Buyuktur, Ayse G. and Hutchful, David K. and Sant, Natasha B. and Nainwal, Satyendra K. , title =. CHI '08 extended abstracts on Human factors in computing systems , year =. doi:10.1145/1358628.1358946 , acmid =

    work page doi:10.1145/1358628.1358946

  30. [34]

    , title =

    Hollis, Billy S. , title =. 1999 , isbn =

    work page 1999

  31. [35]

    Goossens, Michel and Rahtz, S. P. and Moore, Ross and Sutor, Robert S. , title =. 1999 , isbn =

    work page 1999

  32. [36]

    and Rosenberg, Arnold L

    Buss, Jonathan F. and Rosenberg, Arnold L. and Knott, Judson D. , title =. 1987 , source =

    work page 1987

  33. [37]

    CHI '08: CHI '08 extended abstracts on Human factors in computing systems , year =

    , note =. CHI '08: CHI '08 extended abstracts on Human factors in computing systems , year =

    work page

  34. [38]

    Algorithms for Closest-Point Problems (Computational Geometry) , year =

    Clarkson, Kenneth Lee , advisor =. Algorithms for Closest-Point Problems (Computational Geometry) , year =

    work page

  35. [39]

    SIGCOMM Comput. Commun. Rev. , year =

    work page

  36. [40]

    2004 , isbn =

    IEEE TCSC Executive Committee , booktitle =. 2004 , isbn =. doi:http://dx.doi.org/10.1109/ICWS.2004.64 , acmid =

    work page doi:10.1109/icws.2004.64 2004

  37. [41]

    Distributed systems (2nd Ed.) , year =

    work page

  38. [42]

    , title =

    Petrie, Charles J. , title =. 1986 , source =

    work page 1986

  39. [43]

    Donald E. Knuth. Seminumerical Algorithms. 1981

    work page 1981

  40. [44]

    E-commerce and cultural values , year =

    Kong, Wei-Chang , Title =. E-commerce and cultural values , year =

    work page

  41. [45]

    E-commerce and cultural values , year =

    Kong, Wei-Chang , type =. E-commerce and cultural values , year =

    work page

  42. [46]

    Chapter 9 , booktitle =

    Kong, Wei-Chang , editor =. Chapter 9 , booktitle =. 2002 , address =

    work page 2002

  43. [47]

    E-commerce and cultural values , editor =

    Kong, Wei-Chang , title =. E-commerce and cultural values , editor =. 2003 , isbn =

    work page 2003

  44. [48]

    E-commerce and cultural values - (InBook-num-in-chap) , chapter =

    Kong, Wei-Chang , editor =. E-commerce and cultural values - (InBook-num-in-chap) , chapter =. 2004 , address =

    work page 2004

  45. [49]

    E-commerce and cultural values (Inbook-text-in-chap) , chapter =

    Kong, Wei-Chang , editor =. E-commerce and cultural values (Inbook-text-in-chap) , chapter =. 2005 , address =

    work page 2005

  46. [50]

    E-commerce and cultural values (Inbook-num chap) , chapter =

    Kong, Wei-Chang , editor =. E-commerce and cultural values (Inbook-num chap) , chapter =. 2006 , address =

    work page 2006

  47. [51]

    Microelectron

    Mehdi Saeedi and Morteza Saheb Zamani and Mehdi Sedighi , title =. Microelectron. J. , volume =. 2010 , pages =

    work page 2010

  48. [52]

    Mehdi Saeedi and Morteza Saheb Zamani and Mehdi Sedighi and Zahra Sasanian , title =. J. Emerg. Technol. Comput. Syst. , volume =

    work page

  49. [53]

    Kirschmer, Markus and Voight, John , title =. SIAM J. Comput. , issue_date =. 2010 , issn =. doi:https://doi.org/10.1137/080734467 , acmid =

    work page doi:10.1137/080734467 2010

  50. [54]

    Hoare, C. A. R. , title =. Structured programming (incoll) , editor =. 1972 , isbn =

    work page 1972

  51. [55]

    History of programming languages I (incoll) , editor =

    Lee, Jan , title =. History of programming languages I (incoll) , editor =. 1981 , isbn =. doi:http://doi.acm.org/10.1145/800025.1198348 , acmid =

    work page doi:10.1145/800025.1198348 1981

  52. [56]

    , title =

    Dijkstra, E. , title =. Classics in software engineering (incoll) , year =

    work page

  53. [57]

    , title =

    Wenzel, Elizabeth M. , title =. Multimedia interface design (incoll) , year =. doi:10.1145/146022.146089 , acmid =

    work page doi:10.1145/146022.146089

  54. [58]

    , title =

    Mumford, E. , title =. Critical issues in information systems research (incoll) , year =

    work page

  55. [59]

    and Golden, Donald G

    McCracken, Daniel D. and Golden, Donald G. , title =. 1990 , isbn =

    work page 1990

  56. [60]

    The analysis of linear partial differential operators

    H. The analysis of linear partial differential operators. 1985 , PAGES =

    work page 1985

  57. [61]

    IEEE", address =

    A. Adya and P. Bahl and J. Padhye and A.Wolman and L. Zhou , title =. Proceedings of the IEEE 1st International Conference on Broadnets Networks (BroadNets'04) , publisher = "IEEE", address = "Los Alamitos, CA", year =

    work page

  58. [62]

    I. F. Akyildiz and W. Su and Y. Sankarasubramaniam and E. Cayirci , title =. Comm. ACM , volume = 38, number = "4", year =

    work page

  59. [63]

    I. F. Akyildiz and T. Melodia and K. R. Chowdhury , title =. Computer Netw. , volume = 51, number = "4", year =

    work page

  60. [64]

    ACM", address =

    P. Bahl and R. Chancre and J. Dungeon , title =. Proceeding of the 10th International Conference on Mobile Computing and Networking (MobiCom'04) , publisher = "ACM", address = "New York, NY", year =

    work page

  61. [65]

    8 (Special Issue on Sensor Networks)

    D. Culler and D. Estrin and M. Srivastava , title =. IEEE Comput. , volume = 37, number = "8 (Special Issue on Sensor Networks)", publisher = "IEEE", address = "Los Alamitos, CA", year =

    work page

  62. [66]

    Natarajan and M

    A. Natarajan and M. Motani and B. de Silva and K. Yap and K. C. Chua , title =. Network Architectures , editor =. 960935712

    work page

  63. [67]

    Tzamaloukas and J

    A. Tzamaloukas and J. J. Garcia-Luna-Aceves , title =

    work page

  64. [68]

    Zhou and J

    G. Zhou and J. Lu and C.-Y. Wan and M. D. Yarvis and J. A. Stankovic , title =

    work page

  65. [69]

    Mapping Powerlists onto Hypercubes

    Jacob Kornerup. Mapping Powerlists onto Hypercubes. 1994

    work page 1994

  66. [70]

    Automatic Parallelization for Distributed-Memory Multiprocessing Systems

    Michael Gerndt. Automatic Parallelization for Distributed-Memory Multiprocessing Systems

    work page

  67. [71]

    J. E. Archer, Jr. and R. Conway and F. B. Schneider. User recovery and reversal in interactive systems. ACM Trans. Program. Lang. Syst

    work page

  68. [72]

    D. D. Dunlop and V. R. Basili. Generalizing specifications for uniformly implemented loops. ACM Trans. Program. Lang. Syst

    work page

  69. [73]

    Heering and P

    J. Heering and P. Klint. Towards monolingual programming environments. ACM Trans. Program. Lang. Syst

    work page

  70. [74]

    Donald E. Knuth. The book

    work page

  71. [75]

    Korach and D

    E. Korach and D. Rotem and N. Santoro. Distributed algorithms for finding centers and medians in networks. ACM Trans. Program. Lang. Syst

    work page

  72. [76]

    : A Document Preparation System

    Leslie Lamport. : A Document Preparation System

    work page

  73. [77]

    F. Nielson. Program transformations in a denotational setting. ACM Trans. Program. Lang. Syst

    work page

  74. [78]

    Brian K. Reid. A high-level approach to computer document formatting. Proceedings of the 7th Annual Symposium on Principles of Programming Languages

    work page

  75. [79]

    and Abdelzaher, Tarek F

    Zhou, Gang and Wu, Yafeng and Yan, Ting and He, Tian and Huang, Chengdu and Stankovic, John A. and Abdelzaher, Tarek F. , title =. ACM Trans. Embed. Comput. Syst. , issue_date =. doi:10.1145/1721695.1721705 , acmid = 1721705, publisher =

    work page doi:10.1145/1721695.1721705

  76. [80]

    Institutional members of the Users Group

    work page

  77. [81]

    Boris Veytsman , title =

    work page

  78. [82]

    and Peterson, Larry L

    Bowman, Mic and Debray, Saumya K. and Peterson, Larry L. , title =. ACM Trans. Program. Lang. Syst. , volume =. 1993 , doi =

    work page 1993

  79. [83]

    TUGboat , volume =

    Braams, Johannes , title =. TUGboat , volume =

    work page

  80. [84]

    Post Congress Tristesse

    Malcolm Clark. Post Congress Tristesse. TeX90 Conference Proceedings

    work page

Showing first 80 references.