Evaluating Compositional Generalization in Transformers: The Role of Composition Equivalence and Module Coverage

Purva Pruthi, Andrew Yuan, Alexander D'Amour, David Jensen

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

DiLaDiff: Distilled Latent-augmented Diffusion for Language Modeling

DiLaDiff proposes a latent-augmented masked diffusion language model with consistency distillation that improves quality and accelerates inference by generating continuous latents in negligible time.

Jean-Marie Lemercier, Tomas Geffner, Morteza Mardani, Karsten Kreis and 2 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science

A blackboard multi-agent framework lets autonomous agents volunteer for data-discovery tasks, boosting end-to-end success by 13%-57% over rigid master-slave baselines.

Alireza Salemi, Mihir Parmar, Palash Goyal, Yiwen Song and 4 more

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

The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching

Activation patching's natural indirect effect embeds hidden interaction effects between components, which cause conditional importance to be invisible or inflated, explain faithfulness instability, scale with activation distance, and diagnose when greedy component ranking misses combinatorial mechan

Sankaran Vaidyanathan, David Arbour, Aaron Mueller, Scott Niekum and 1 more

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

RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents

RICE-PO turns retrieval interactions into localized credit signals to train reasoning agents, outperforming RL baselines on BRIGHT and BEIR.

mingchen li, Hansi Zeng, Zhuo Qian, Jiatan Huang and 3 more

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