data science

2,431 papers

#artificial intelligence Preprint Open access Oct 2026

On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance

Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how model-internalized priors interact with user-provided instructions. We investigate three dimensions of this interaction: (1) how an LLM's familiarity with data and task definitions r...

Etienne Casanova, Rafal Kocielnik, R. Michael Alvarez · 0 citations

#artificial intelligence Preprint Open access Oct 2026

Escaping the Capacity Ceiling: Routing on the Stiefel Manifold for Bilinear SPD Layers

Deep networks on the symmetric positive-definite (SPD) manifold promise expressive representations by encoding data geometry as an inductive bias, but stacking BiMap layers with the standard ReEig nonlinearity often adds no capacity: on real, preconditioned EEG data, ReEig rarely activates, so the stack behaves as a si...

Isabella C. Maia, Salem Said, Pedro L. C. Rodrigues et al. · 0 citations

#artificial intelligence Preprint Open access Oct 2026

AREX: Affine-Residual Exponential Integrator for Few-Step Sampling in Flow Matching

We introduce AREX, a training-free sampler for pretrained flow matching models that uses the target mean and covariance to capture an analytically tractable part of the sampling dynamics. We show that the velocity field of the moment-matched Gaussian target is the $L^2$-optimal affine approximation to the marginal velo...

Shizheng Lin, Soon Hoe Lim, N. Benjamin Erichson · 0 citations

#artificial intelligence Preprint Oct 2026

Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback

We study fixed-confidence best-arm identification under strict 1-bit feedback constraints. At each round, the learner selects an arm and a query set, and receives only a single bit indicating whether the sampled reward belongs to that set. We consider a distribution-free finite-variance setting with arm-wise localizati...

Khang A. Luong, Sơn Thái Đinh, Ho-Ang Ta et al. · 0 citations

Reach audiences

Advertise in front of researchers, engineers, and readers.

See ad packages

#artificial intelligence Preprint Oct 2026

Generalization Bounds for Flow-matching Generative Models for Intrinsically Low-dimensional Data

Despite the remarkable empirical success of flow-matching models, their statistical generalization guarantees remain underdeveloped. Existing analyses often impose restrictive assumptions on the estimated velocity field and yield convergence rates that fail to reflect the intrinsic low-dimensional structure common in r...

Saptarshi Chakraborty, Quentin Berthet, Peter L. Bartlett · 6 citations · ⚡1

#artificial intelligence Preprint Open access Oct 2026

Learning Style, Forgetting Semantics: A Case Study of SFT and RFT on Classification Tasks

Why does supervised fine-tuning (SFT) lead to more forgetting than reinforcement fine-tuning (RFT), even when all teacher demonstrations are semantically correct? We study this question on classification tasks where tokens within each semantic class express the same semantic answer in different styles. The tasks share...

Haodong Liang, Yanhao Jin, Krishnakumar Balasubramanian et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Counterfactual Predictions in Scientific Emulators Without Controlled Experiments

Many scientific questions require reasoning about what was never observed: What if the conditions, interventions, or history had been different? Models can predict accurately on observed data yet fail on such what-if queries when correlated inputs are varied independently. A common remedy is to add controlled simulatio...

Ding-Ling Yao, Kahaan Gandhi, Valentin Duruisseaux et al. · 0 citations