arXiv:2601.19403v1 Announce Type: cross Abstract: Obstructions such as raindrops, fences, or dust degrade captured images, especially when mechanical cleaning is infeasible. Conventional solutions to obstructions rely on a bulky compound optics array or computational inpainting, which compromise compactness or fidelity. Metalenses composed of subwavelength meta-atoms promise compact imaging, but simultaneous achievement of broadband and obstruction-free […]
Cortex-Grounded Diffusion Models for Brain Image Generation
arXiv:2601.19498v1 Announce Type: cross Abstract: Synthetic neuroimaging data can mitigate critical limitations of real-world datasets, including the scarcity of rare phenotypes, domain shifts across scanners, and insufficient longitudinal coverage. However, existing generative models largely rely on weak conditioning signals, such as labels or text, which lack anatomical grounding and often produce biologically implausible outputs. To […]
Randomization Boosts KV Caching, Learning Balances Query Load: A Joint Perspective
arXiv:2601.18999v1 Announce Type: cross Abstract: KV caching is a fundamental technique for accelerating Large Language Model (LLM) inference by reusing key-value (KV) pairs from previous queries, but its effectiveness under limited memory is highly sensitive to the eviction policy. The default Least Recently Used (LRU) eviction algorithm struggles with dynamic online query arrivals, especially in […]
Detecting and Correcting Hallucinations in LLM-Generated Code via Deterministic AST Analysis
arXiv:2601.19106v1 Announce Type: cross Abstract: Large Language Models (LLMs) for code generation boost productivity but frequently introduce Knowledge Conflicting Hallucinations (KCHs), subtle, semantic errors, such as non-existent API parameters, that evade linters and cause runtime failures. Existing mitigations like constrained decoding or non-deterministic LLM-in-the-loop repair are often unreliable for these errors. This paper investigates whether […]
SHIELD: An Auto-Healing Agentic Defense Framework for LLM Resource Exhaustion Attacks
arXiv:2601.19174v1 Announce Type: cross Abstract: Sponge attacks increasingly threaten LLM systems by inducing excessive computation and DoS. Existing defenses either rely on statistical filters that fail on semantically meaningful attacks or use static LLM-based detectors that struggle to adapt as attack strategies evolve. We introduce SHIELD, a multi-agent, auto-healing defense framework centered on a three-stage […]
Structure-based RNA Design by Step-wise Optimization of Latent Diffusion Model
arXiv:2601.19232v1 Announce Type: cross Abstract: RNA inverse folding, designing sequences to form specific 3D structures, is critical for therapeutics, gene regulation, and synthetic biology. Current methods, focused on sequence recovery, struggle to address structural objectives like secondary structure consistency (SS), minimum free energy (MFE), and local distance difference test (LDDT), leading to suboptimal structural accuracy. […]
Instance-Guided Radar Depth Estimation for 3D Object Detection
arXiv:2601.19314v1 Announce Type: cross Abstract: Accurate depth estimation is fundamental to 3D perception in autonomous driving, supporting tasks such as detection, tracking, and motion planning. However, monocular camera-based 3D detection suffers from depth ambiguity and reduced robustness under challenging conditions. Radar provides complementary advantages such as resilience to poor lighting and adverse weather, but its […]
Teaching Machine Learning Fundamentals with LEGO Robotics
arXiv:2601.19376v1 Announce Type: cross Abstract: This paper presents the web-based platform Machine Learning with Bricks and an accompanying two-day course designed to teach machine learning concepts to students aged 12 to 17 through programming-free robotics activities. Machine Learning with Bricks is an open source platform and combines interactive visualizations with LEGO robotics to teach three […]
APC-RL: Exceeding Data-Driven Behavior Priors with Adaptive Policy Composition
arXiv:2601.19452v1 Announce Type: cross Abstract: Incorporating demonstration data into reinforcement learning (RL) can greatly accelerate learning, but existing approaches often assume demonstrations are optimal and fully aligned with the target task. In practice, demonstrations are frequently sparse, suboptimal, or misaligned, which can degrade performance when these demonstrations are integrated into RL. We propose Adaptive Policy […]
Scale-Consistent State-Space Dynamics via Fractal of Stationary Transformations
arXiv:2601.19551v1 Announce Type: cross Abstract: Recent deep learning models increasingly rely on depth without structural guarantees on the validity of intermediate representations, rendering early stopping and adaptive computation ill-posed. We address this limitation by formulating a structural requirement for state-space model’s scale-consistent latent dynamics across iterative refinement, and derive Fractal of Stationary Transformations (FROST), which […]
Up to 36x Speedup: Mask-based Parallel Inference Paradigm for Key Information Extraction in MLLMs
arXiv:2601.19613v1 Announce Type: cross Abstract: Key Information Extraction (KIE) from visually-rich documents (VrDs) is a critical task, for which recent Large Language Models (LLMs) and Multi-Modal Large Language Models (MLLMs) have demonstrated strong potential. However, their reliance on autoregressive inference, which generates outputs sequentially, creates a significant efficiency bottleneck, especially as KIE tasks often involve […]
Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward
arXiv:2601.19055v1 Announce Type: cross Abstract: We study how to fine-tune LLMs using user-edit deployment data consisting of a set of context, an agent’s response, and user edits. This deployment data is naturally generated by users in applications such as LLMs-based writing assistants and coding agents. The _natural_ origin of user edits makes it a desired […]