Mean-Field Parallel Decoding for Discrete Diffusion Language Models

Tamim Zoabi, Ameen A Ali, Liran Ringel, Lior Wolf

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

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation

Shani Goren, Ido Galil, Ran El-Yaniv

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

More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding

Noam Elata, Itay Lamprecht, Mikey Shechter, Daniel Ohayon and 2 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

Learnable Spectral Activations

Tamir Shor, Or Litany, Alex M Bronstein

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

Competing Event Models: Next Event Prediction Under Interventions

Yoav Wald, Xiang Gao, Sumit Chopra, Juho Lee and 1 more

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

Harnessing Data Asymmetry in Manifold Learning

Thomas Dagès, Simon Weber, Daniel Cremers, Ron Kimmel

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

Finite Resources False Discovery Rate Control on Structured Hypothesis Spaces

Binyamin Perets, Shie Mannor

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

How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs

Mark Kozdoba, Shie Mannor

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

Positional Encoding Is All You Need For Scalable Equivariance Constraint Relaxation

Hagay Michaeli, Haggai Maron, Daniel Soudry

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

Split-RL: Local Conflict Resolution in Reinforcement Learning

Benjamin Fuhrer, Chen Tessler, Gal Dalal

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

Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching

Adaptive batching policies process multi-step lookahead via state-dependent batches, yielding near-optimal regret bounds for tabular reinforcement learning.

Nadav Merlis

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

Selective Safety Steering via Value-Filtered Decoding

Value-filtered decoding selectively steers LLM generation using a value-based safety criterion with explicit false-intervention bounds, improving safety-utility trade-offs over baselines.

Bat-Sheva Einbinder, Hen Davidov, Yee Whye Teh, Yarin Gal and 1 more

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

STRABLE: Benchmarking Tabular Machine Learning with Strings

STRABLE introduces 108 real-world string-and-number tables and benchmarks 445 pipelines, finding simple embeddings with advanced learners suffice for categorical tables while LLMs help on free-text tables.

Gioia Blayer, Myung Jun Kim, Félix Lefebvre, Lennart Purucker and 7 more

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

MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image

MulTaBench benchmarks 40 multimodal tabular datasets and shows target-aware tuning of text and image embeddings improves predictive performance over frozen embeddings.

Alan Arazi, Eilam Shapira, Shoham Grunblat, Mor Ventura and 7 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026 · ▲ 142 on Hugging Face

Learning Reveals Invisible Structure in Low-Rank RNNs

Deriving reduced ODEs for low-rank RNN learning reveals loss-invisible overlaps that encode training history and expose hidden connectivity differences.

Yoav Ger, Omri Barak

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

Controllable User Simulation

Controllable user simulation is formalized as causal inference, proving supervised fine-tuning injects look-ahead bias causing geometric variance explosion and controllability collapse, with proposed mitigations restoring consistency and robust generalization.

Guy Tennenholtz, Ofer Meshi, Amir Globerson, Uri Shalit and 2 more

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

Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees

Applying CVaR to the immediate belief cost targets per-step state uncertainty while preserving standard MDP structure, enabling any expectation-based planner to become risk-sensitive with unchanged algorithms and end-to-end finite-time guarantees.

Yaacov Pariente, Vadim Indelman

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

Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning

Graph Sparse Sampling shares sampled futures across actions to avoid exponential horizon dependence in continuous MDP planning, with polynomial sample bounds and strong long-horizon control performance.

Idan Lev-Yehudi, Vadim Indelman

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

SP-CACW: Convergence-Aware Client Weighting for Selfish Personalized Learning

SP-CACW minimizes an upper bound on a target client's convergence error via convergence-aware weighting that trades peer bias against variance and excludes harmful peers.

Yaron Kiselman, Kfir Y. Levy

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models

DEMASK predicts token dependencies in discrete diffusion language models to select weakly dependent masked positions for parallel unmasking, bounding sampling error and accelerating Dream-7B by 1.7, 2.2× with preserved accuracy.

Liran Ringel, Ameen A Ali, Yaniv Romano

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