We investigate the extent to which an LLM's hidden-state geometry can be recovered from its behavior in psycholinguistic experiments. Across eight instruction-tuned transformer models, we run two experimental paradigms -- similarity-based forced choice and free association -- over a shared 5,000-word vocabulary, collec...
Louis Schiekiera, Max Zimmer, Christophe Roux et al.· 0 citations
Reinforcement learning (RL) post-training is a dominant approach for improving the reasoning performance of large language models (LLMs), yet growing evidence suggests that its gains arise primarily from distribution sharpening rather than the acquisition of new capabilities. Recent work has shown that sampling from th...
Xiaotong Ji, Rasul Tutunov, Matthieu Zimmer et al.· 0 citations
Differential privacy limits how much each training image can influence a medical imaging model but lowers its diagnostic accuracy. Pretrained weights reduce this loss. It is unknown whether the pretraining objective or domain improves accuracy more. Here we train chest radiograph classifiers under differential privacy...
Soroosh Tayebi Arasteh, Mina Farajiamiri, Mahshad Lotfinia et al.· 0 citations
An operation's input-output function does not, by itself, determine its computational role within a represented process. That role also depends on the processes producing its inputs and receiving its outputs, a philosophical stance termed deep learning externalism (DLE). We develop a mathematical account of represented...
Luis F. Rosario Freytes· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Alignment in large language models (LLMs) is still largely static: after training, the policy is frozen. DPO, GRPO methods typically imprint one behavior into the weights, leaving little runtime control beyond prompt hacks or expensive re-alignment. We introduce ECLIPTICA, which treats alignment as instruction-driven a...
Kapil Wanaskar, Gaytri Jena, Vinija Jain et al.· 0 citations
Multimodal Large Language Models (MLLMs) have substantially advanced Radiology Report Generation (RRG), yet aligning them through reinforcement learning (RL) remains challenging due to heterogeneous medical supervision. Vanilla Group Relative Policy Optimization (GRPO) assigns uniform credit across the entire generatio...
Applying well-established statistical methods effectively to LLM evals requires consideration of model correlations and prediction noises. Leading evals often ignore data noise, have low statistical power, or make unnecessary trade-offs. We define and measure three types of noise: 1) prediction noise from generating di...
Neuroeconomics appears to offer welfare economics an evidential supplement, since neural data may help distinguish choices that express genuine preferences from choices distorted by addiction, framing or self-control failure. This paper asks when such evidence can legitimately inform welfare judgements for policy. It d...
The Segment Anything Model (SAM) family has become a widely adopted vision foundation model, but its ability to control segmentation granularity remains limited. Users often need to refine results manually - by adding more prompts or selecting from pre-generated masks - to achieve the desired level of detail. This proc...
This paper presents Naga, a deep State Space Model (SSM) encoding approach inspired by structural concepts from Vedic mathematics. The proposed method introduces a bidirectional representation for time series by jointly processing forward and time-reversed input sequences. These representations are then combined throug...
Melanie Schaller, Nick Janssen, Bodo Rosenhahn· 0 citations
Faster convergence is the remaining target for an end-to-end gain in forward-only deep learning, and a pre-registered ablation identifies gradient detachment, not MF's auxiliary losses, as the dominant factor tested.
Flat minima are strongly associated with improved generalisation in deep neural networks. However, this connection has proven nuanced in recent studies, with both theoretical counterexamples and empirical exceptions emerging in the literature. In this paper, we revisit the role of sharpness in model performance and exa...
Israel Mason-Williams, Gabryel Mason-Williams, Helen Yannakoudakis· 0 citations
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
