DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion

Yongji Long, Shijun Liang, Jintao Li, Yun Li

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

Understanding Graph Self-Supervised Pre-training under Distribution Shifts: A Scaling Law Perspective

Bingheng Li, Shikun Liu, Yu Song, Jay Revolinsky and 4 more

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

$f$-GRPO & Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment

Rajdeep Haldar, Lantao Mei, Guang Lin, Yue XING and 1 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

REINS: Learning Inertia-Induced Geometry for Physics-Consistent Motion Representation in Clinical Gait Phenotyping

Yiran Ding, Yufei Zhang, Zijun Cui

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

SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?

Kean Shi, Zihang Li, Tianyi Ma, Zengji Tu and 11 more

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

Self-Supervised Doppler-Guided RF Odometry

Kunzhe Song, Jialuo Du, Jingkai Lin, Huacheng Zeng

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

LogicDirector: Enforcing Temporal Composition in Text-to-Video Generation

Yujiang Pu, Zixu Cheng, Shaogang Gong, Handong Zhao and 1 more

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

Dynamic Convolutions Improve Transformers

Oliver Sieberling, Bharat Runwal, Rameswar Panda, Yoon Kim

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

Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives

Xiang Li, Yixuan Jia, Xiao Li, Jeffrey Fessler and 2 more

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

Rethinking Geometric Depth in Monocular 3D Object Detection: A Projection-Consistent Reformulation

Zhihao Zhang, Abhinav Kumar, Huaizhi Qu, Tianlong Chen and 1 more

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

Firefly: Illuminating Verified Real-world Tool Call Data Generation

Yuxuan Lu, Ziyi Wang, Yingzhou Lu, Yisi Sang and 11 more

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

Minimax-Optimal Transformer Classification for Functional Data with Dense-Sparse Phase Transition

Shuoyang Wang, Yidan Tian, Guanqun Cao

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

Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design

Chain-of-Generation progressively decomposes prompts into curriculum-ordered segments to guide multi-stage latent diffusion, improving text-aligned molecular design with greater controllability and interpretability.

Lingxiao Li, Haobo Zhang, Bin Chen, Jiayu Zhou

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

Language-Induced Priors for Domain Adaptation

Using expert text descriptions to build LLM-derived priors guides domain selection under scarce target data, yielding near-oracle cold-start error and asymptotic consistency.

Qiyuan Chen, Jiayu Zhou, Raed AL Kontar

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

Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning

Biometric identity provisioning allocates virtual face identities as non-colliding gaps within the real identity manifold, scaling to ten million embeddings and one million photorealistic images via gap-aware generation.

Yuyang Ji, Yixuan Shen, Anil Jain, Xiaoming Liu and 1 more

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

SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perception

SapiensID 2.0 aligns human recognition with perception via soft-biometrics, noise disentanglement, and kinematic attention to achieve state-of-the-art re-identification and gait recognition.

Yiyang Su, Jie Zhu, Feng Liu, Anil Jain and 1 more

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

Structural Rationale Distillation via Reasoning Space Compression

D-RPC distills reasoning via reusable reasoning paths to stabilize supervision, improving student performance with fewer tokens.

Jialin Yang, Jiankun Wang, Jiajun Wu, Henry Leung and 2 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization

Subspace gradient orthogonalization unifies low-rank projection with spectral optimization into ZO-Muon, cutting zeroth-order queries by 75% versus MeZO while boosting accuracy on LLM and vision fine-tuning.

Yicheng Lang, Changsheng Wang, Yihua Zhang, Mingyi Hong and 3 more

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

PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion

PixelDense aligns pixel diffusion with frozen dense-prediction teachers via separate semantic and geometric projection streams and orthogonality penalties, improving GenEval to 0.8093 and training speed by 1.23x.

Lehan Yang, Daiqing Qi, Wenhao Zhang, Avery Li and 8 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 20 on Hugging Face · Code ★ 3

Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration

3DSPMR leverages 3D spatial memory with field-of-view geometric priors to reuse exploration knowledge across sequential embodied tasks, significantly improving reasoning and navigation performance on the SEER-Bench benchmark.

Zhongyi Cai, Yi Du, Chen Wang, Yu Kong

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

Consilience for Verifier-Free Test-Time Scaling

Confidence-based verifier-free test-time scaling fails on complex tasks because high initial confidence signals no exploration; consilience selects rollouts by requiring low early but high final confidence, improving reasoning and coding.

Lecheng Kong, Like Hui, Haitao Mao, Luke Huan

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

SPANUQ: Span-Level Uncertainty Quantification for Large Language Model Generation

SPANUQ is a lightweight probe that estimates span-level LLM generation uncertainty via hidden-state distillation, outperforming sampling methods with 10, 20x speedups and 0.910 F1 span detection.

Yimeng Zhang, Yingying Zhuang, Ziyi Wang, Yuxuan Lu and 11 more

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

Crafting Reversible SFT Behaviors in Large Language Models

LCDD constructs sparse, causally necessary subnetworks for SFT behaviors, and SFT-Eraser reverses them via activation-matched soft prompts without weight changes.

Yuping Lin, Pengfei He, Yue XING, Yingqian Cui and 4 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

A Principled Self-Referenced Early Stopping Approach for Deep Image Prior

Proposed pseudo self-referenced early stopping for Deep Image Prior uses constructed image pairs to detect overfitting, outperforming existing methods across inverse imaging problems without requiring noise level estimates.

Chaoyan Huang, Cheng-Han Huang, Ismail Alkhouri, Rongrong Wang

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

L-FAME: Longitudinal Focused Attention Meditation EEG Dataset and Benchmark

L-FAME offers a longitudinal EEG dataset and benchmark of 74 participants across three meditation practices over six weeks, with baseline classification and cross-session adaptation results.

Angqi Li, Basit R Syed, Hamzeh Alzweri, Taosheng Liu and 2 more

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