AI News · Models & Methods
Machine learning news: training methods, data, evaluation and ML engineering in production.
373 stories · Updated
373 stories
arXiv:2610.37652v2 Announce Type: replace-cross Abstract: Dexterous manipulation with multi-fingered hands is the next frontier of robotics, yet learned hand skills remain limited to simple grasps or basic repeated motions, such as rotating an object. As robots attempt more demanding in-hand maneuvers, safety, such as…
arXiv:2611.01047v2 Announce Type: replace-cross Abstract: Composers develop music from an original idea, controlling how similar each new section is to it, from near repetition to new material. Game music needs this often, as its material repeats over long play. Music models, however, rarely learn to control…
arXiv:2611.01993v2 Announce Type: replace-cross Abstract: When an image classifier decides, we can usually only estimate why. For quantum and all-optical classifiers that act linearly on amplitude-encoded pictures up to the measurement, with no trained classical network before or after them, each class's Born…
arXiv:2611.02566v2 Announce Type: replace-cross Abstract: The rapid growth of automated code generation has created a pressing need for automated code review. Yet code review resists full automation: it depends on context beyond the \textit{diff}, on the author's intent, and on judgments about design and…
Depth pruning removes entire transformer blocks and therefore depends on a reliable criterion for identifying which blocks can be removed. Block Influence (BI) ranks blocks by how minimally they rotate the hidden state. However, local redundancy does not necessarily imply downstream irrelevance. We address this…
Reinforcement learning (RL) algorithms are effective in solving problems that can be modeled as Markov decision processes (MDPs). These algorithms primarily target forward MDPs whose dynamics evolve over time from an initial state. However, several important problems in different scenarios including stochastic control…
Graph-aware calibrators make graph neural networks (GNNs) more trustworthy by predicting a temperature for each node, usually with auxiliary networks whose decisions are hard to inspect. We propose Interpretable Structural Temperature Scaling (ISTS), a twelve-parameter linear model that sets each node's temperature…
Low-rank adaptation (LoRA) enables parameter-efficient fine-tuning but can suffer from redundant basis directions. Constraining the basis factor to the Stiefel manifold addresses this redundancy through orthonormality. Landing methods allow temporarily infeasible iterates to explore a neighborhood of the manifold…
Genomic foundation models (GFMs) have emerged as a powerful paradigm for learning DNA sequence representations, yet existing self-supervised pretraining strategies overlook alternative splicing and underperform compared to specialized models. To address this gap, we introduce IsoAlign, a multimodal framework that…
Concept erasure is a prominent approach to achieving fairness in machine learning through the removal of sensitive attributes from learned representations. Prior concept erasure methods typically define debiasing indirectly through the failure of a chosen adversary, probe, or fairness penalty, which makes the target…