Learning Matters
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Self-supervised Learning Matters: A Simple Ensemble Solution for Micro-Gesture Recognition
arXiv:2606.09261v1 Announce Type: new Abstract: In this paper, we present XInsight Lab's solution to the micro-gesture classification track of the 4th MiGA Challenge at IJCAI 2026, in which our solution ranked first and achieved a new state-of-the-art result. We propose a multimodal ensemble framework that integrates a self-supervised RGB-based model with supervised multi-stream models from previous solutions. The self-supervised RGB model is pretrained on 120K unlabeled clips via masked...
Learning What Matters: Probabilistic Task Selection via Mutual Information for Model Finetuning
arXiv:2507.12612v3 Announce Type: replace Abstract: Supervised fine-tuning performance for large language models depends strongly on how training budget is distributed across a heterogeneous set of tasks. In practice, mixtures are often fixed using simple heuristics (e.g., uniform or size-proportional sampling) that ignore task interactions, which can hurt transfer and waste budget on redundant sources. We introduce TaskPGM, a framework for learning continuous task mixtures via an...
PictSure: Pretraining Embeddings Matters for In-Context Learning Image Classifiers
Announce Type: replace Abstract: Building image classification models remains cumbersome in data-scarce domains, where collecting large labeled datasets is impractical. In-context learning (ICL) is a promising paradigm for few-shot image classification (FSIC), but prior work has underexplored the relative importance of encoder pretraining versus fusion-layer training data. We present PictSure, a vision-only ICL family of models that demonstrates the potential of easy-to-use fusion...
Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation
arXiv:2509.03456v2 Announce Type: replace-cross Abstract: Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits. Recent advances in OPL primarily optimize OPE estimators with improved statistical properties, assuming that better estimators inherently yield superior policies. Although theoretically justified, this estimator-centric approach neglects a critical practical obstacle: challenging optimization landscapes.
SALT: When More Rollouts Don't Help in Group-Based Policy Optimization and How to Make Them Matter
Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) often adopts GRPO-style group-relative updates, sampling multiple rollouts per prompt to construct normalized learning signals. However, merely increasing the number of rollouts does not reliably strengthen learning: under GRPO-style group normalization, per-rollout policy-gradient features can concentrate into a low-rank, signed geometry, causing substantial cancellation during aggregation and weakening the...
Names Don't Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning
arXiv:2601.23169v2 Announce Type: replace Abstract: Current neural architectures lack a principled way to handle interchangeable tokens, i.e., symbols that are semantically equivalent yet distinguishable, such as bound variables. As a result, models trained on fixed vocabularies often struggle to generalize to unseen symbols, even when the underlying semantics remain unchanged. We propose a novel Transformer-based mechanism that is provably invariant to the renaming of interchangeable tokens.
Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter
arXiv:2602.06842v2 Announce Type: replace Abstract: Deep learning-based hybrid iterative methods (DL-HIMs) integrate classical numerical solvers with neural operators, utilizing their complementary spectral biases to accelerate convergence. Despite this promise, many DL-HIMs stagnate at false fixed points where neural updates vanish while the physical residual remains large, raising questions about reliability in scientific computing. In this paper, we provide evidence that performance is...
Learning to Perceive the World Through Control: Empowerment-Based Representation Learning
arXiv:2605.30656v1 Announce Type: new Abstract: In many practical reinforcement learning environments, observations are far higher-dimensional than the variables that matter for control. In this work, we ask: can we learn representations that capture only control-relevant features of the environment? We study this question through the empowerment objective, which maximizes an agent's influence over the environment and is widely used for unsupervised skill learning.
Short-Term Developmental Trajectories of Dorsal-Ventral Pathways and Their Relationships with First-Grade Learning
The first year of formal schooling is a year of foundational reading and math learning, and individual differences emerging within this single year predict academic achievement decades later. Yet, how brain changes throughout this critical year relate to individual differences in reading and math learning remains uncharacterized. In this pre-registered study (https://osf.io/97ybe), we acquired monthly both behavioral assessments of reading- and math-learning, and diffusion-weighted MRI scans...