CtrlCache: Accelerating Interactive Video World Models with Control-Aware Caching

CtrlCache accelerates interactive video world models via control-aware caching that detects action changes to reuse transformer residuals and apply frequency-mixed history guidance, achieving up to 1.41x speedups with improved quality.

Shangye Song, Dong Gong, Hong Jia, Yun Sing Koh and 1 more

Published Oct 6, 2026 · ▲ 1 on Hugging Face · Code

GeoSET: Generalist Foundation Model for SAR-to-EO Image Translation

GeoSET is a generalist SAR-to-EO translation model pretrained on 3 million diverse pairs and adapted via LoRA, achieving state-of-the-art results across six benchmarks.

Jeonghyeok Do, Munchurl Kim

Published Sep 26, 2026 · 0 citations · ▲ 6 on Hugging Face · Code ★ 3

Adaptive Fused Prior Transfer for Controllable Generative Image Compression

AFP-GIC transfers adaptive fused priors from a frozen pretrained model to guide generative compression without transmitting them, reducing decoder latency and parameters while improving very-low-bitrate naturalness.

Yifei Pei, Ying Liu, Nam Ling

Published May 16, 2026 · ▲ 4 on Hugging Face · Code ★ 4

NIV: Neural Axis Variations for Variable Font Generation

Nadav Benedek, Ariel Shamir, Ohad Fried

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Sample-Efficient Optimization over Generative Priors via Coarse Learnability

Pranjal Awasthi, Sreenivas Gollapudi, Ravi Kumar, Kamesh Munagala

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

CrossID: Cross-Supervised Spatio-Temporal Gated Fusion for Personalized Portrait Generation

Dongxu Yue, Qixin Yan, Shiao Yang, Xiaoqiang Zhou and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Few-Shot Visual Concept Extraction for Steering Diffusion Transformers

Nabyl Quignon, Antitza Dantcheva

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

ControlSVG: Exploring Controllable SVG Generation with Autoregressive Models

Qirui Li, Teng Hu, Ran Yi, Paul L Rosin and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

AdDirector: Anchored Guidance for Generating Camera-Controllable Advertisement Videos

Shiyue Zhang, Zheng Chong, Xiangkun Shi, Xiaojian Lin and 6 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

FlowTrack: Controlling Edit-Signal Execution in Inversion-Free Flow Video Editing

Jielun Zhong, Di Wang, Jisheng Dang, Leigang Qu and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

OverLay++: Dense-Overlap Layout-to-Image Generation Dataset

Shivansh Aggarwal, Shresth Grover, Divyansh Srivastava, Haiyang Xu and 6 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

TopoRefine: Topology-Aware Correspondence and Residual Refinement for Training-Free Subject-Consistent Generation

Zhanxin Gao, Zexin Ti, Chen Zhao, Beier Zhu and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

MobTA: Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic

SHUAI LIU, Ning Cao, Yue Jiang, Gao Cong

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation

Guo Tang, Yongtao Wang

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation

Shan Xiaojun, Haoyu Shen, Yucheng Mao, Haiyang Xu and 4 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Anymotion: A Dataset, Benchmark, and Baseline for Controllable Human Motion Editing

Haiyang Yan, Jianxin Sun, Yuhan Wu, libin wang and 4 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

WaveletLoRA: Frequency-Aware Content-Style Decomposition for Personalized Image Generation

Peiyao Wang, Jiahui Sun, Weining Wang, Jing Liu

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

GPA: Generative Population Annealing for Test-Time Sequence Design with Pretrained Generative Models

Anirban Sarkar, Alejandra Duran, Peter Koo

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Learning Cultural Vectors for Cross-Cultural Generation

Sina Malakouti, Deepti Ghadiyaram, Boqing Gong, Adriana Kovashka

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

$SE(2)$-Aware Conditional Distribution Transport for Vehicle Trajectory Generation

Di Wen, Zhaocheng He, Shuhui Wang

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion

Yushi LAN, Zeren Jiang, Koichi Namekata, Xingang Pan and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

MorphGen: Controllable Cell-Image Generation with Biological Representation Alignment

Berker Demirel, Marco Fumero, Theofanis Karaletsos, Francesco Locatello

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

ChiP-STAR: Spatial-Topological Attention for Pre-trained Generative Chip Routing

Junfeng Liu, Xingquan Li

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

DeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition

Zhiqiang Wu, Shuang Sun, Jiale Zhang, Jing Li and 3 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

GeoFidelity-Bench: Evaluating Block-Conditioned Geographic Fidelity of Street-View Generation

Kaizhen Tan

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Distilling Conditional Image Generators into Spatial Effect Maps

Eun Ryung Lee, Seyoung Park

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

FlashControl: One-Step Controllable Generator via Distillation-Friendly Single-Stream Teachers.

Ngan Nguyen, Dung Nguyen, Quan Dao, Dimitris Metaxas and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

From Heartbeat to Cardiochoreography: A Mechanics Foundation Model for Individualized 4D Cardiac Motion Generation Conditioned on Electrophysiology

Ziquan Wei, Tingting Dan, Guorong Wu

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

A latent control model for realistic rodent motion

Aidan Sirbu, Charles Y Zhang, Yuanjia Yang, Bence Olveczky and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel

Jayoung Ryu, Kyunghyun Cho, Romain Lopez

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

MDMR-Bench: A Multi-Dimensional Benchmark for Multi-Reference Image Generation

Bowen Zheng, Jintao Lin, Chang-Heng Yi, HAORAN YANG and 4 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

Learning Preference Representations for Preference-Conditioned Image Generation

Wenyi Mo, Tianyu Zhang, Yalong Bai, Ligong Han and 2 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

ProGraf: Profile-Guided Planning for Step-by-Step Generation of Structured Non-Natural Images

Ran Luo, Haoxiang Deng, Lan Zhang, Mu Yuan

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Generative Conformal Prediction with Optimized Coverage Allocation

Minxing Zheng, Shixiang Zhu

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

TaxaAdapter: Scaling Fine-grained Species Image Generation To the Tree of Life

Mridul Khurana, Amin Karimi Monsefi, Justin Lee, Medha Sawhney and 8 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis

Haoxiang Cao, Yuxuan Zhang, Penghui Du, Bo Li and 15 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

MorphSIG: Subject-Driven Image Generation via Decoupled Anchoring and Feature Transport

Hailong Yan, Yongrui Zhang, Xiangtao Zhang, Le Zhang

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Towards more general control of diffusion models using Jeffrey Guidance

Jeffrey guidance extends diffusion control by updating marginals via Jeffrey's rule, reducing FID and enforcing fairness.

Raphaël Razafindralambo, Rémy Sun, Frederic Precioso, Jes Frellsen and 1 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation

RIG-BENCH evaluates reasoning-driven image generation across four cognitive domains, revealing that state-of-the-art models produce locally plausible but globally illogical outputs.

Yutong Liu, Nan Huang, Xu Cao, James Rehg

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 2 on Hugging Face

Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization

Exploiting spherical latent geometry yields nearly closed-form Bayesian optimization with 100x speedups and matching performance in generative discovery pipelines.

Donney Fan, Colin Doumont, Aleksandra Kalisz, Paul Duckworth and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues

SierpinskiCam augments geometry guidance with Sierpinski dome texture cues and reference video conditioning to improve camera-controlled video retaking across large viewpoint changes.

Suttisak Wizadwongsa, Hyelin Nam, Supasorn Suwajanakorn, Jeong Joon Park

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control

LA-LQR applies reduced-order linear optimal control to steer video generation activations via anticipative feedback, reducing unsafe outputs while preserving visual quality.

Jihoon Hong, Alice Chan, Qiyue Dai, Julian Skifstad and 1 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization

FashionChameleon enables real-time interactive multi-garment video customization via teacher in-context learning, streaming distillation, and KV cache rescheduling, achieving 23.8 FPS and 30-180x speedups.

Quanjian Song, Yefeng Shen, Mengting Chen, Hao Sun and 3 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 65 on Hugging Face · Code ★ 284

Calibrating Generative Models to Feature Distributions with MMD Finetuning

kCGM minimizes feature-level MMD with unbiased score estimators and KL regularization to calibrate generative models to target distributions without overfitting, improving feature matching and validity across molecular, protein, and DNA tasks.

Nathaniel L. Diamant, Brian L Trippe

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models

A mean-field framework formulates inference-time diffusion control via weighted interacting particles to target distribution-level rewards with theoretical guarantees.

Samuel Howard, Nikolas Nüsken

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image Generation

TrioPose uses a triple-stream pose-aware DiT with relational bias masks and spatial loss weighting to generate accurate multi-person images, improving Human-Art AP by 30%.

dian gu, Zhengyi Yang

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Test-Time Conditioning with Representation-Aligned Visual Features

REPA-G uses representation-aligned visual features to steer diffusion sampling at inference time via optimized similarity, enabling precise multi-scale and multi-concept conditioning without retraining.

Nicolas Sereyjol-Garros, Ellington Kirby, Victor Letzelter, Victor Besnier and 1 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization

AnchorWorld improves egocentric world simulation via full-body interaction supervision and anchor-view customization with consistent spatio-temporal dynamics.

Yu Li, Menghan Xia, Gongye Liu, Xintao Wang and 7 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 30 on Hugging Face

Active Learning for Conditional Generative Compressed Sensing

For conditional generative compressed sensing, prompt-matched Christoffel sampling achieves near-optimal recovery bounds while prompt mismatch adds explicit penalties, with experiments showing prompts reshape sensing and recovery.

Alexander DeLise, Nick Dexter

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation

COLLAR progressively optimizes object-level diffusion features via field-of-view expansion to improve conditional generation quality and spatial control without training.

Xinlong Zhang, Jia Wei, Xiaoyu Zhang, Teng Zhou and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Assessing Sample Quality in Conditional Generation under Compositional Shift

A per-sample trust score combining global realism and attribute-wise faithfulness evaluates conditional generations under compositional shift without reference data, enabling filtering and ranking that improves biological imaging and vision benchmarks.

Berker Demirel, Valentino Maiorca, Marco Fumero, Theofanis Karaletsos and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Why Cross-Skeleton Retargeting Is Non-Identifiable: Structural Limits of Generative Motion Models

Cross-skeleton retargeting is structurally non-identifiable: unpaired training yields gauge ambiguity and paired training collapses to conditional means, so source fidelity requires new diagnostics and objectives.

Zhiyuan Li, Wenyan Yang, Pekka Marttinen, Joni Pajarinen

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Follow the Mean: Reference-Guided Flow Matching

Flow matching enables controllable generation via reference-guided mean shifts without fine-tuning, yielding training-free control and swappable semi-parametric guidance.

Pedro Curvo, Maksim Zhdanov, Floor Eijkelboom, Jan-Willem van de Meent

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 2 on Hugging Face · Code ★ 25

Controllable Generative Sandbox for Causal Inference

CausalMix couples mixture Gaussian latent priors with type-specific decoders to generate realistic mixed-type tabular data with explicit, independent control over overlap, confounding, and treatment effect heterogeneity.

Qi Zhang, Harsh Parikh, Ashley I Naimi, Razieh Nabi and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation

UniVL embeds visual and textual instructions into spatial masks for contextual image generation, cutting FID to 11 and inference costs by 52% without a text encoder.

Jiayun (Peter) Wang, Yu Wang, Weijie Gan, Zhenting Wang and 1 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion

NP-LoRA fuses subject and style LoRAs via null-space projection to reduce subspace interference, improving controllable generation without retraining.

Chuheng Chen, Xiaofei Zhou, Geyuan Zhang, Yong Huang and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

When Metropolis and Hastings Meet Bradley and Terry: Exact MCMC From Preference Voting

Pref-MH samples from judge-conditioned distributions via exact Metropolis-Hastings using only stochastic binary pairwise preferences and converges to the target with optimal acceptance rules.

Ariel Smogorghevski, Nir Rosenfeld, Yaniv Romano

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

PISCO: Precise Video Instance Insertion with Sparse Control

PISCO enables precise video instance insertion via sparse keyframe control while preserving dynamics, achieving monotonic gains with added signals and outperforming editing baselines.

Xiangbo Gao, Renjie Li, Xinghao Chen, Yuheng Wu and 4 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 13 on Hugging Face · Code ★ 62

Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation

Conditioning diffusion models on multimodal large language models with VAE identity conditioning and dual-layer aggregation improves subject-driven generation by balancing semantics with identity preservation.

Shuhong Zheng, Aashish K Misraa, Kevin Li, Yu-Jhe Li and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 7 on Hugging Face

Exploring MLLM-Diffusion Information Transfer with MetaCanvas

MetaCanvas enables multimodal LLMs to plan directly in diffusion latent spaces, outperforming global-conditioning baselines across six precise visual generation tasks.

Han Lin, Xichen Pan, Ziqi Huang, Ji Hou and 9 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 15 on Hugging Face

Hallucination in World Models is Predictable and Preventable

World models hallucinate in low-coverage state-action regions, and coverage-aware sampling plus curiosity rewards detect and mitigate it with minimal data.

Nick Hansen, Xiaolong Wang

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

UniCustom: Unified Visual Conditioning for Multi-reference Image Generation

UniCustom fuses visual-semantic and appearance features before VLM encoding to eliminate cross-reference confusion in multi-reference image generation. Experiments show improved subject consistency, instruction following, and compositional fidelity over baselines.

Yiyan Xu, Qiulin Wang, Wenjie Wang, Yunyao Mao and 4 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

TrajLoc: Trajectory-Attention Localization for Multi-Object Motion Control

TrajLoc isolates per-object attention via Gaussian heatmaps to control multi-object motion, improving trajectory adherence by 51% and PSNR by 4.3 dB.

Omer Sela, Inbar Huberman-Spiegelglas, Michael Rotman, Sagie Benaim and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face · Code ★ 2

Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation

Auteur introduces a human-centric DSL and virtual director to generate language-driven camera trajectories for human-centered video synthesis, outperforming existing methods on framing metrics.

Muhammed Burak Kızıl, Enes Sanli, Niloy Mitra, Xuelin Chen and 3 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

VicEdit: Learning to Edit Videos from Visual In-Context Examples

VicEdit enables visual in-context video editing via multi-modal guidance and achieves state-of-the-art results on instruction and visual reference tasks.

Yuji Wang, Teng Hu, Yuheng Chen, Ran Yi and 5 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text

T2Mo generates dynamic 3D shapes via feed-forward conditioning on 3D trajectories and text, with shape-grounded trajectory embeddings handling arbitrary trajectory densities to improve motion fidelity.

Jaeyeong Kim, Inès H Kim, Jahyeok Koo, Seungryong Kim

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026