All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow

Wei Dong, Han Zhou, Terry Ji, Guanhua Zhao and 5 more

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

CoScan: Multi-Scale Content-Adaptive Space-Filling Scans for Causal State-Space Image Restoration

Wei Dong, Terry Ji, Yan Min, Shahram Shirani and 2 more

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

Phase Transitions in Heavy-Tailed Mean Estimation under $\ell_p$ Norms

Ishaq Aden-Ali, Yeshwanth Cherapanamjeri, Mikael Møller Høgsgaard, Kasper Green Larsen and 1 more

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

AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment

Eric Zhang, Terry J Zhang, Chijioke Ugwuanyi, Jerick Shi and 2 more

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

Multi-Marginal Couplings for Metropolis--Hastings

Multi-marginal coupling of Metropolis-Hastings chains via shared-randomness Poisson Monte Carlo improves coalescence rates and reduces meeting times up to 50%.

Truong Buu Phan, Gergely Flamich, Ashish Khisti, Shahab Asoodeh

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

From Table to Cell: Attention for Better Reasoning with TABALIGN

TABALIGN improves multi-step table reasoning by pairing diffusion planners generating binary cell masks with attention verifiers, raising accuracy 15.76 points and accelerating execution 44.64%.

Tung Sum Thomas Kwok, Zeyong Zhang, Xinyu Wang, Chunhe Wang and 5 more

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

Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns

SkillMigrator learns reusable web skills via transferable interaction patterns matched by layout similarity to reduce LLM actions 8-10% across WebArena and Mind2Web.

Shiqi He, Yue Cui, Feijie Wu, Xinyu Ma and 4 more

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

Online Finetuning Decision Transformers with Pure RL Gradients

Removing hindsight relabeling enables stable pure-RL online finetuning of Decision Transformers via adapted GRPO with sub-trajectory optimization and active sampling, achieving state-of-the-art results.

Junkai Luo, Yinglun Zhu

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

Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples

Classification fields recursively generate infinite hierarchical cluster structures via local parent-to-child refinement rules learnable from finite prefixes with exponential convergence guarantees.

Yicen Li, Ruiyang Hong, Anastasis Kratsios, Haitz Sáez de Ocáriz Borde and 1 more

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