Speech representations from self-supervised speech models (S3Ms) are known to be sensitive to phonemic contrasts, but their sensitivity to prosodic contrasts has not been directly measured. The ABX discrimination task has been used to measure phonemic contrast in S3M representations via minimal pairs. We introduce pros...
Haitong Sun, Stephen McIntosh, Kwanghee Choi et al.· 0 citations
This work introduces Fast-Slow Thinking Reward Models (F/S-RM), a hybrid RM architecture inspired by Dual Process Theory that achieves state-of-the-art accuracy with an average score of 84.3 across benchmarks, while reducing token consumption by 22.5%.
Large language models (LLMs) exhibit strong performance on self-contained programming tasks. However, they still struggle with repository-level software engineering (SWE), which demands (1) deep codebase navigation with effective context management for accurate localization, and (2) systematic approaches for iterative,...
Rule-to-Tag (R2T), a framework that turns linguistic rules into the training signal for neural sequence taggers in low-resource languages, is introduced, a first instance of a broader paradigm the authors call principled learning (PrL): using explicit principles as a learning signal, rather than relying on example-base...
Mamadou K. Keita, Christopher Homan, Sébastien Diarra· 2 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Choosing a Large Language Model (LLM) for a given task requires comparing many strong candidates, yet standard evaluation relies on costly annotations over fixed evaluation sets. To address this challenge, we develop SELECT-LLM, the first framework for active model selection of LLMs. SELECT-LLM aims to find a small set...
Yavuz Durmazkeser, Patrik Okanovic, Andreas Kirsch et al.· 0 citations
LaSEr-Edit is proposed, a constraint-satisfying text revision method that can be applied to any LLMs, black- or white-box, and it is found that lightweight, task-specific energy-based models (EBMs) achieve error-localization performance competitive with or even better than that of much larger LLMs, while operating subs...
H. Son, Saehee Eom, Mooho Song et al.· 3 citations
Granularity alignment, not algorithm choice, localizes when routing helps, and what category supervision buys when deployed through routing is quantified.
EpiKV is introduced, which combines hidden-state shifts with the model's recent query--key relevance to rank cached tokens without materializing the attention matrix, and matches or outperforms the strongest attention-based eviction baselines while running directly in vLLM with unmodified attention kernels.
Steven Kolawole, Virginia Smith· arXiv.org· 2 citations
It is shown that harness-aware post-training not only improves in-distribution performance but also enables agents to robustly adapt to OOD settings, highlighting the importance of harness-aware post-training under such shifts.
Kyungmin Kim, Youngbin Choi, Seoyeon Lee et al.· arXiv.org· 7 citations
A post-hoc certification framework forparse autoencoders that provides a practical way to determine whether an SAE representation preserves enough of a frozen LM's predictive behavior to support certification of the original model.
Drop-by-Drop is proposed, a novel multi-bitwidth post-training quantization framework enabling inference-time precision control over LLM weights from a single quantized model, and it is proved that Gaussian sources are successively refinable under a weighted mean squared error distortion motivated by LLM loss functions...
Liza Babaoglu, Shuangyi Chen, Ashish J. Khisti· arXiv.org· 1 citation
Claw-SWE-Bench is introduced, a unified benchmark that enables researchers to systematically assess the capabilities and efficiency of general-purpose harnesses on software engineering tasks and guide the development of more capable and efficient harnesses.
Meng-Yu Zheng, Kai Han, Bo-Xun Li et al.· arXiv.org· 5 citations
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduSep 24, 2026
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
