37 papers
Two-atom Dicke model with atom-atom interaction
Lin Jiao, Han Pu
Interactions among emitters provide a powerful means of controlling collective light--matter phenomena, yet their role in superradiant criticality has not been thoroughly investiga…
The Parser Already Knows: Lightweight Bias Correction in Constrained Decoding
Işıl Özgü, Yaoxuan Wu, Guy Van den Broeck +1
Grammar Constrained Decoding (GCD) forces Language Models (LMs) to produce syntactically valid outputs by masking out non-conforming tokens at each step. However, rigid masking dis…
Making Embodied AI Reliable: A Community Agenda from Testing to Formal Verification
Xi Zheng, Dulanga Weerakoon, Yintong Huo +8
Embodied AI systems are increasingly deployed in open-world environments, yet ensuring their reliability remains a fundamental challenge. Drawing on discussions from the AAAI'26 Br…
Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
Meihua Dang, Linxin Song, Honghua Zhang +3
Generations from large language models often fail to conform to desired constraints such as JSON schema. Existing locally constrained decoding (LCD) approaches enforce constraints…
ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts
Heng Zhao, Zilei Shao, Guy Van den Broeck +1
Mixture-of-Experts (MoE) models scale by activating only a small subset of experts per token. However, training such models remains challenging because top- routing is discrete…
The Pitfalls of KV Cache Compression
Alex Chen, Renato Geh, Aditya Grover +2
KV cache compression promises increased throughput and efficiency with negligible loss in performance. While the gains in throughput are indisputable and recent literature has inde…