The Geometry-Adaptive Explainer (GAE), which realigns the dictionary with the OOD-active subspace while preserving the original sparse feature activations, and bound the excess projection loss caused by any remaining faithfulness gap.
Sung-Jun Lim, Heedong Kim, A. Lee et al.· arXiv.org· 0 citations
On-Policy Distillation (OPD) has emerged as a dominant post-training paradigm for Large Language Models, especially in reasoning domains. However, OPD remains unstable in practice due to the high gradient variance of its single-sample Monte Carlo estimator, and recipes for stable training are still immature. We propose...
Minjae Oh, Sangjun Song, Gyubin Choi et al.· 0 citations
Integrated Policy Gradient is introduced, a novel, training-free framework that brings policy-based attribution into mechanistic interpretability for LLM reasoning and enables modulation of reasoning capabilities, offering a powerful and reliable framework for understanding LLM reasoning.
Chang-Ming Li, Kai-Xin Zhang, Haoyun Xu et al.· 4 citations
A domain-adaptive small language model (SLM) with an encoder-decoder architecture for the enhanced prediction of product and service tax codes and demonstrates the superior performance of the domain-adaptive encoder-decoder SLMs over flat classifiers when applied to the Harmonized System of Nomenclature.
S. Nath, S. Wadhwa, Luis Perez· arXiv.org· 5 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
We propose Online Latent prediction with Invariant Views and rEconstruction (OLIVE), a self-supervised speech representation learning framework that jointly optimizes analysis and synthesis objectives. OLIVE couples masked latent prediction and waveform reconstruction through a functional separation within a single enc...
An empirical analysis of three training-time interventions that raise accepted draft length by 21-76% per benchmark over a position-uniform baseline, without adding additional forward passes and without changing the inference pipeline or the rejection-sampling exactness contract.
L. Whalen, Yuki Ito, Ryo Sakamoto· arXiv.org· 4 citations
This work proposes Distillation through Reasoning Path Compression (D-RPC), which constrains the teacher to follow a compact, dynamically maintained bank of reusable high-level reasoning paths, and achieves the highest average accuracy among the evaluated distillation methods.
State Space Models (SSMs) such as Mamba have become a popular alternative to Transformer models, due to their reduced memory consumption and higher throughput at generation compared to their Attention-based counterparts. On the other hand, the community has built up a considerable body of knowledge on how to train Tran...
Psychological scale refinement traditionally relies on response-based methods such as factor analysis, item response theory, and network psychometrics to uncover latent constructs and optimize item composition. Although rigorous, these approaches require large samples and may be constrained by data availability and cro...
Bo Wang, Yuxuan Zhang, Yueqin Hu et al.· 0 citations
This paper proposes a systematic framework for synthesizing high-quality, population-aligned persona sets for LLM-driven social simulation, and introduces a task-specific module that adapts the globally aligned persona set to targeted subpopulations.
This work addresses the first need with controlled context enrichment, a set of prompt substitution rules that systematically enriches distinct types of context: neutral padding, generic social background, descriptive decision grounding, and normative decision grounding, and finds that these forms of enrichment produce...
Mattia Greiche, Reihaneh Rabbany, Maximilian Puelma Touzel· 0 citations
Small language models offer a compact basis for shell simulation without executing submitted commands, but full-output decoding requires them to predict recurring utility structure alongside content that varies across executions. We introduce template gap reconstruction (TGR), which supplies reusable output literals in...
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.
MIT News · Artificial Intelligence· news.mit.eduOct 28, 2026
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 27, 2026
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
