Pith. sign in

REVIEW 32 cited by

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1709.07871 v2 pith:XT37AZWG submitted 2017-09-22 cs.CV cs.AIcs.CLstat.ML

FiLM: Visual Reasoning with a General Conditioning Layer

classification cs.CV cs.AIcs.CLstat.ML
keywords filmreasoningconditioninglayersvisualfeature-wiseneuralablations
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - answering image-related questions which require a multi-step, high-level process - a task which has proven difficult for standard deep learning methods that do not explicitly model reasoning. Specifically, we show on visual reasoning tasks that FiLM layers 1) halve state-of-the-art error for the CLEVR benchmark, 2) modulate features in a coherent manner, 3) are robust to ablations and architectural modifications, and 4) generalize well to challenging, new data from few examples or even zero-shot.

discussion (0)

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

Forward citations

Cited by 32 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Diffusion-warm sampling of the XY model enables fast thermalization at scale

    quant-ph 2026-06 unverdicted novelty 7.0

    A temperature-conditioned diffusion model trained on small XY lattices produces accurate larger-lattice samples and cuts MCMC thermalization time by roughly 10x.

  2. ConTex: Reformulating Counterfactual Generation For Time Series Forecasting

    cs.LG 2026-06 unverdicted novelty 7.0

    ConTex learns a global intervention strategy via a decomposed temporal-conditional encoder architecture to generate consistent, sparse counterfactuals for time series models in a single forward pass.

  3. DGLD: Domain-Gated Latent Diffusion for the Discovery of Novel Energetic Materials

    physics.chem-ph 2026-05 unverdicted novelty 7.0

    DGLD applies domain-gated latent diffusion with label-quality gating and multi-task guidance to discover 12 novel energetic material leads validated by DFT, outperforming SMILES-LSTM, SELFIES-GA, and REINVENT baseline...

  4. Field-level multi-tracers simulation-based inference of cosmological parameters from 3D maps

    astro-ph.CO 2026-05 unverdicted novelty 7.0

    The work demonstrates that multi-tracer field-level SBI on galaxy and HI maps yields 2-7 times better constraints on Omega_m and sigma_8 than single-tracer or summary-statistic approaches, with 3D maps performing best.

  5. Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social Attention

    cs.AI 2026-05 unverdicted novelty 7.0

    DiffLNS uses a discrete diffusion initializer to produce warm-start plans that lift LNS2 success rates to 95.8% across 20 congested MAPF settings, generalizing from 96 to 312 agents.

  6. SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data

    cs.LG 2026-05 unverdicted novelty 7.0

    SeBA is a joint-embedding framework that separates tabular data into two complementary views and aligns one view's representations to the nearest-neighbor structure of the other, improving feature-label relationships ...

  7. Radio-Interferometric Image Reconstruction with Denoising Diffusion Restoration Models

    astro-ph.IM 2026-01 unverdicted novelty 7.0

    A diffusion model trained on real radio galaxy images reconstructs high-fidelity interferometric observations from VLA, EHT, and ALMA simulations and outperforms CLEAN on gridded visibilities.

  8. Diffusion Models Beat GANs on Image Synthesis

    cs.LG 2021-05 accept novelty 7.0

    Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.

  9. FLORA: A deep learning approach to predict forest attributes from heterogeneous LiDAR data

    cs.CV 2026-06 unverdicted novelty 6.0

    FLORA is an octree-based deep learning framework with auxiliary data fusion that predicts forest attributes from heterogeneous LiDAR, achieving rRMSE of 12.3% for dominant height and 39% for total volume on 32k French...

  10. Relevance Is Not Permission: Warranted Attention for Value Contributions

    cs.AI 2026-06 unverdicted novelty 6.0

    Warrant adds learned permission gates g_ij to attention value terms alpha_ij * v_j, improving primary metrics in 27 of 32 comparisons across CTDG, MTPP, RAG, STPP, and TKG tasks.

  11. Relevance Is Not Permission: Warranted Attention for Value Contributions

    cs.AI 2026-06 unverdicted novelty 6.0

    Warrant adds a query-item permission gate g_ij to attention value terms, improving primary metrics in 27 of 32 comparisons across CTDG, MTPP, RAG, STPP, and TKG tasks.

  12. Attention mechanism for scalable mesh-based neural surrogates of free-surface fluids

    cs.CE 2026-06 unverdicted novelty 6.0

    Self-attention mechanisms are used to build mesh-preserving neural surrogates that approximate PFEM dynamics for free-surface flows, delivering accurate transient predictions and improved scalability on 2D and 3D benchmarks.

  13. Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching

    cs.LG 2026-06 unverdicted novelty 6.0

    Presents adjoint matching for scalable max-ent RL training of diffusion policies, enabling simulation-free optimization.

  14. Conditional Graph Diffusion for Negotiation Support: Overcoming Discrete Infeasibility and Preference Elicitation Gaps

    cs.GT 2026-06 unverdicted novelty 6.0

    Conditional Graph Diffusion generates continuous negotiation outcomes with high individual rationality using GATv2 encoders, cross-attention fusion, and inference-time normative guidance gradients.

  15. A General Differentiable Ray-Wave Framework for Hybrid Refractive-Diffractive System Modeling and Optimization

    physics.optics 2026-05 unverdicted novelty 6.0

    A plug-and-play differentiable model bridging ray and wave optics for hybrid systems that enables end-to-end optimization of planar and conformal diffractive elements.

  16. MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning

    cs.LG 2026-05 unverdicted novelty 6.0

    MoMo conditions contrastive representations and prediction operators on user preferences via FiLM and low-rank modulation to enable continuous modulation of plan safety while preserving inference efficiency.

  17. MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning

    cs.LG 2026-05 unverdicted novelty 6.0

    MoMo uses Feature-Wise Linear Modulation and low-rank neural modulation to condition contrastive planning representations on user preferences while preserving inference efficiency and probability density ratios.

  18. Self-Supervised Spatial And Zero-Shot Angular Super-Resolution by Spatial-Angular Implicit Representation For Rotating-View SNR-Efficient Diffusion MRI

    cs.CV 2026-05 unverdicted novelty 6.0

    SA-INR achieves self-supervised spatial super-resolution and zero-shot angular super-resolution in rotating-view dMRI from single-view acquisitions per direction, reaching 34.82 dB PSNR on trained and 33.08 dB on unse...

  19. Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation

    cs.RO 2026-04 unverdicted novelty 6.0

    Lucid-XR uses XR-headset physics simulation and physics-guided video generation to create synthetic data that trains robot policies transferring zero-shot to unseen real-world manipulation tasks.

  20. The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation

    cs.LG 2026-04 conditional novelty 6.0

    Knowledge conflicts in hypernetwork LLM adaptation stem from constant adapter margins losing to frequency-dependent pretrained margins; selective layer boosting and conflict-aware triggering raise deep-conflict accura...

  21. Train-Small Deploy-Large: Leveraging Diffusion-Based Multi-Robot Planning

    cs.RO 2026-04 unverdicted novelty 6.0

    A diffusion-based multi-robot planner trained on few agents generalizes to larger numbers during deployment using inter-agent attention and temporal convolution.

  22. AE-ViT: Stable Long-Horizon Parametric Partial Differential Equations Modeling

    cs.LG 2026-04 unverdicted novelty 6.0

    AE-ViT combines a convolutional autoencoder with a latent-space transformer and multi-stage parameter plus coordinate injection to deliver stable long-horizon predictions for parametric PDEs, cutting relative rollout ...

  23. Forecasting implied volatility surface with generative diffusion models

    q-fin.CP 2025-11 unverdicted novelty 6.0

    A conditioned diffusion model with SNR-weighted arbitrage penalty generates one-day-ahead arbitrage-free implied volatility surfaces and outperforms baselines on market data.

  24. Local Diffusion Models and Phases of Data Distributions

    cs.LG 2025-08 unverdicted novelty 6.0

    The paper introduces a phase framework for data distributions connected by local denoisers and demonstrates that reverse diffusion consists of trivial and data phases separated by a transition where local score functi...

  25. Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation

    cs.CV 2019-07 unverdicted novelty 6.0

    EC-CNN uses a gated feature-wise transform to incorporate edge priors for thermal semantic segmentation and introduces the SODA dataset of over 7,000 labeled thermal images.

  26. Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models

    cs.SD 2026-06 unverdicted novelty 5.0

    Causal probing of attention in audio separation transformers identifies dual pathways and asynchronous convergence, enabling a training-free Layer-Selective Attention Caching method that reduces self-attention computa...

  27. TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation

    cs.RO 2026-06 unverdicted novelty 5.0

    TAM is a policy-agnostic torque adaptation module trained in randomized simulation that improves zero-shot real-robot performance on dynamic manipulation tasks compared to system identification and RMA baselines.

  28. SPADE: Sketch-guided Path Planning Augmented with Diffusion Experts

    cs.RO 2026-06 unverdicted novelty 5.0

    SPADE combines sketch-guided path planning with diffusion-augmented imitation learning to achieve better generalization and lower error with fewer parameters than prior methods.

  29. LEIA: Learned Environment for Interactive Architected Materials

    cs.LG 2026-05 unverdicted novelty 5.0

    LEIA is a world model for autoregressive 3D simulation of architected materials under interactive loading, benchmarked on MicroPlate and applied to surrogate-guided de novo design search with finite-element validation.

  30. Federated Medical Image Classification under Class and Domain Imbalance exploiting Synthetic Sample Generation

    cs.CV 2026-04 unverdicted novelty 5.0

    FedSSG generates and shares synthetic samples within a federated setup to reduce class imbalance and domain shift problems in medical image classification.

  31. The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation

    cs.LG 2026-04 unverdicted novelty 5.0

    Knowledge conflicts in hypernetwork LLM adaptation stem from constant adapter margins losing to frequency-dependent pretrained margins; selective layer boosting and conflict-aware triggering close the gap.

  32. Revisiting Integration of Image and Metadata for DICOM Series Classification: Cross-Attention and Dictionary Learning

    eess.IV 2026-02 unverdicted novelty 5.0

    Proposes a multimodal model with cross-attention and missingness-aware dictionary learning for robust DICOM series classification that outperforms image-only, metadata-only, and other multimodal baselines on liver MRI...