Task-oriented Alignment ( ToAlign) should be proactively under the itself.

Of the useful features, which ones does the model use? Of the task-irrelevant features, which ones does the model represent?

Abstract--Grasping accuracy is a critical prerequisite for precise object manipulation, often requiring careful alignment between the robot hand and object. Neural Descriptor Fields (NDF) offer a promising vision-based method to generate grasping poses that generalize across object categories. However, NDF alone can produce inaccurate poses due to imperfect camera calibration, incomplete point clouds, and object variability. Meanwhile, tactile sensing enables more precise contact, but existing approaches typically learn policies limited to simple, predefined contact geometries. In this work, we introduce NeuralT ouch, a multi-modal framework that integrates NDF and tactile sensing to enable accurate, generalizable grasping through gentle physical interaction. Our approach leverages NDF to implicitly represent the target contact geometry, from which a deep reinforcement learning (RL) policy is trained to refine the grasp using tactile feedback. This policy is conditioned on the neural descriptors and does not require explicit specification of contact types. Results show that NeuralT ouch significantly improves grasping accuracy and robustness over baseline methods, offering a general framework for precise, contact-rich robotic manipulation. I. INTRODUCTION A commonplace behaviour in humans is our ability to glance at an object to determine its general position and then use touch alone to grasp it with precision.

In this section, we provide an extensive and comprehensive display of experiments. Following that, we evaluate OLDM in cross-model scenarios as the third subsection. Di Lin is the corresponding author of this paper. By default, we set M = 50 . By default, we use λ = 0 . In Figure 3, we investigate the effectiveness of different threshold settings.

Polysemanticity is pervasive in language models and remains a major challenge for interpretation and model behavioral control. Leveraging sparse autoencoders (SAEs), we map the polysemantic topology of two small models (Pythia-70M and GPT-2-Small) to identify SAE feature pairs that are semantically unrelated yet exhibit interference within models. We intervene at four loci (prompt, token, feature, neuron) and measure induced shifts in the next-token prediction distribution, uncovering polysemantic structures that expose a systematic vulnerability in these models. Critically, interventions distilled from counterintuitive interference patterns shared by two small models transfer reliably to larger instruction-tuned models (Llama-3.1-8B/70B-Instruct and Gemma-2-9B-Instruct), yielding predictable behavioral shifts without access to model internals. These findings challenge the view that polysemanticity is purely stochastic, demonstrating instead that interference structures generalize across scale and family. Such generalization suggests a convergent, higher-order organization of internal representations, which is only weakly aligned with intuition and structured by latent regularities, offering new possibilities for both black-box control and theoretical insight into human and artificial cognition.