Activation steering turns localized representations into control directions, but localization alone does not reveal whether a direction has a selective operating regime. We introduce Predictive Memory Localization (PML), which treats the measured-grid intervention path as the predictive object of memory localization.
arXiv:2608. 12892v1 Announce Type: new Abstract: Activation steering turns localized representations into control directions, but localization alone does not reveal whether a direction has a selective operating regime.
arXiv:2606. 31208v1 Announce Type: new Abstract: Large tabular models (LTMs), i.
arXiv:2608. 01130v1 Announce Type: new Abstract: A broad range of models face the mismatch where they are updated through trajectory losses but are evaluated by downstream task reward.
Dataset distillation (DD) condenses large corpora into compact, information-rich subsets for efficient training and reuse. However, under noisy supervision, DD risks condensing corrupted associations together with useful signals, degrading robustness.
arXiv:2606. 08365v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to steer language models, but feature steering is rarely clean: the same intervention can behave inconsistently across contexts and perturb unrelated features.
arXiv:2606. 09396v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation and often serves as the initialization stage for reinforcement learning (RL), but it can show weaker generalization than RL.
arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.
Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution. However, because this supervision is generated via uncontrolled sampling, it provides no diagnostic insight into the model's specific errors or corrective guidance for its individual failure patterns.
arXiv:2601. 18699v2 Announce Type: replace Abstract: Sequential fine-tuning of Large Language Models (LLMs) adaptation to target tasks often triggers catastrophic forgetting, where the acquisition of novel target skills degrades ancestral capabilities.
arXiv:2606. 03080v1 Announce Type: cross Abstract: Causal language models factorize sequence probabilities using only preceding context, leaving future information unexploited during training despite its availability in the training data.
arXiv:2606. 18844v1 Announce Type: new Abstract: Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution.
arXiv:2604. 16197v2 Announce Type: replace Abstract: Data attribution and valuation are critical for understanding data-model synergy for Large Language Models (LLMs), yet existing gradient-based methods suffer from scalability challenges on LLMs.