Compositional Literary Primitives in Instruction-Tuned LLMs: Cross-Architectural SAE Features for Self, Style, and Affect
arXiv:2605.18808v1 Announce Type: cross Abstract: We characterize a compositional architecture of literary primitives in two instruction-tuned large language models (Llama…
WriteSAE: Sparse Autoencoders for Recurrent State
arXiv:2605.12770v3 Announce Type: replace-cross Abstract: We introduce WriteSAE, the first sparse autoencoder that decomposes and edits the matrix cache write…
Vision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation
arXiv:2605.16393v1 Announce Type: cross Abstract: Semantic segmentation is essential for analysing anatomical features in biomedical research, yet a performance gap…
$boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
arXiv:2605.17862v1 Announce Type: cross Abstract: Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution…
Overcoming the Intrinsic Performance Limitations of MEMS IMU via Diffusion-Based Generative Learning
arXiv:2605.16391v1 Announce Type: cross Abstract: Inertial measurement units (IMUs) are fundamental sensing components in multi-source integrated navigation systems, and their…
When Does Non-Uniform Replay Matter in Reinforcement Learning?
arXiv:2605.10236v3 Announce Type: replace-cross Abstract: Modern off-policy reinforcement learning algorithms often rely on simple uniform replay sampling and it remains…
SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
arXiv:2604.09297v2 Announce Type: replace-cross Abstract: Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet…
Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization
arXiv:2605.17839v1 Announce Type: cross Abstract: Knowledge distillation transfers knowledge from a high capacity teacher to a compact student using a…
ClawArena: Benchmarking AI Agents in Evolving Information Environments
arXiv:2604.04202v2 Announce Type: replace-cross Abstract: AI agents deployed as persistent assistants must maintain correct beliefs as their information environment evolves.…
AgentWall: A Runtime Safety Layer for Local AI Agents
arXiv:2605.16265v1 Announce Type: new Abstract: The safety of autonomous AI agents is increasingly recognized as a critical open problem. As…