What determines the quality of a tabular foundation model? Unlike language or vision, tabular foundation models acquire their inductive biases almost entirely from synthetic pretraining distributions, yet the design of these distributions remains poorly understood. Standard synthetic priors are too well-behaved: they o...
Mohamed Bouadi, Nassim Bouarour, Varun Kulkarni et al.· 0 citations
Vision-language models (VLMs) perform strongly on multimodal benchmarks, yet their ability to reliably follow continuous visual structure remains unclear. We focus on path following, a basic operation that requires following a selected path through successive visual continuations. Before considering complex factors suc...
Hyesoo Hong, Min Soo Kim, Wonje Jeung et al.· 0 citations
Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems. Current LLM agents lack this flexibility, as their scaffolds hard-code such reas...
Dean Light, Michael Theologitis, Kshitish Ghate et al.· 0 citations
We present Attractor-Vascular Coupling Theory (AVCT), a theory-guided framework for deriving interpretable blood pressure (BP) predictors from photoplethysmography (PPG) attractor geometry. AVCT connects vascular dynamics, PPG observation, delay-coordinate reconstruction, and attractor descriptors within a unified fram...
Balancing exploration with exploitation is a core challenge in black-box optimization and reinforcement learning. We introduce POETS ($\textbf{Po}$licy $\textbf{E}$nsembles for $\textbf{T}$hompson $\textbf{S}$ampling), a novel framework that bridges uncertainty quantification and policy optimization. Our approach is gr...
Nicolas Menet, Andreas Krause, Abbas Rahimi· 0 citations
Most existing LLM diagnoses are evaluated on static, single-turn settings where complete patient information is provided upfront, an oversimplification of real clinical practice. We study active diagnosis: the real-life clinical process of starting from initial observation, ordering tests, interpreting results, and upd...
Hsin-Ling Hsu, Zizheng Wang, Donghua Zhang et al.· 0 citations
We present a novel theoretical framework, Q-MMR, for off-policy evaluation in finite-horizon MDPs. Q-MMR learns a set of scalar weights, one for each data point, such that the reweighted rewards approximate the expected return under the target policy. The weights are learned inductively in a top-down manner via a momen...
Large language models (LLMs) contain functionally distinct modules with heterogeneous gradient statistics. Although Adam(W) adapts updates at the parameter level, selecting relative learning rates across modules often relies on costly manual tuning. We study this problem through gradient signal-to-noise ratio (SNR). Ou...
Ziqing Wen, Zhouyang Liu, Jiahuan Wang et al.· 0 citations
Reward models are central to LLM alignment, yet current benchmarks reveal little about how they represent diverse and sometimes competing social preferences. We extend reward model evaluation to four socially consequential domains: bias, safety, morality, and ethical reasoning. Our analysis shows that strong benchmark...
Equity Bias is a philosophical and practical framework for building more equitable AI systems. It treats AI as an interpretive agent that constructs meaning and knowledge rather than as a neutral calculator. Grounded in Gadamerian hermeneutics and epistemic injustice theory, Equity Bias views bias not as an error to el...
Training capable software engineering (SWE) agents demands large-scale, executable, and verifiable environments that provide dynamic feedback loops for iterative code editing, test execution, and solution refinement. However, existing open-source datasets remain limited in scale and repository diversity, while industri...
Dayuan Fu, Shenyu Wu, Yunze Wu et al.· 0 citations
Existing locate-then-edit Knowledge Editing (KE) methods typically decompose editing into two stages: upstream target representation optimization and downstream constrained parameter optimization. The optimization across the two stages is disconnected: upstream applies uniform regularization without observing downstrea...
