arXiv:2503.02170v3 Announce Type: replace-cross Abstract: Domain shift remains a persistent challenge in deep-learning-based computer vision, often requiring extensive model modifications or large labeled datasets to address. Inspired by human visual perception, which adjusts input quality through corrective lenses rather than over-training the brain, we propose Lens, a novel camera sensor control method that enhances model […]
Memory-Augmented Reinforcement Learning Agent for CAD Generation
arXiv:2605.19748v1 Announce Type: new Abstract: Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation methods based on large language models (LLMs) often fall short when handling complex CAD models characterized by long operation sequences, diverse operation types, and strong geometric constraints, primarily because reasoning chains […]
Chunking German Legal Code
arXiv:2605.19806v1 Announce Type: cross Abstract: This paper investigates chunking strategies for retrieval-augmented generation on German statutory law, using the German Civil Code as a structured benchmark corpus. We implement and compare a range of segmentation approaches, including structural units (sections, subsections, sentences, propositions), fixed-size windows, contextual chunking, semantic clustering, Lumber-style chunking, and RAPTOR-based hierarchical retrieval. […]
What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code
arXiv:2605.19762v1 Announce Type: new Abstract: Code has become a standard component of modern foundation language model (LM) training, yet its role beyond programming remains unclear. We revisit the claim that code improves reasoning through controlled pretraining experiments on a 10T-token corpus with fine-grained domain separation. Our findings are threefold. First, when code is restricted to […]
HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing
arXiv:2605.08143v2 Announce Type: replace-cross Abstract: Large language models encode vast factual knowledge that can become outdated or incorrect after deployment, yet retraining is prohibitively costly. This motivates lifelong model editing, which updates targeted behavior while preserving the rest of the model. Existing editors, both parameter-modifying and parameter-preserving, degrade severely as edits accumulate and struggle to […]
Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
arXiv:2602.04998v2 Announce Type: replace-cross Abstract: Low-Rank Adaptation (LoRA) is the prevailing approach for efficient large language model (LLM) fine-tuning. Building on this paradigm, recent studies have proposed alternative initialization strategies, architectural modifications, and optimization adjustments, reporting substantial improvements over vanilla LoRA. However, these gains are often demonstrated under fixed or narrowly tuned hyperparameter settings, despite […]
Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement
arXiv:2605.19317v1 Announce Type: cross Abstract: Inference-time scaling has emerged as a major approach for improving reasoning capabilities, and has been increasingly applied to diffusion models. However, existing inference-time scaling methods for diffusion models typically rely on external verifiers or reward models to rank and select samples, limiting their scalability to settings where such evaluators are […]
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
arXiv:2605.07721v2 Announce Type: replace-cross Abstract: Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space without generating intermediate tokens. Models such as Ouro perform reasoning by iteratively updating internal representations while retaining a standard Key-Value (KV) cache across iterations, causing memory consumption to grow […]
DEFLECT: Delay-Robust Execution via Flow-matching Likelihood-Estimated Counterfactual Tuning for VLA Policies
arXiv:2605.19294v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are typically deployed with asynchronous inference: the robot executes a previously predicted action chunk while the model computes the next one. This creates a prediction-execution misalignment: the chunk is conditioned on the observation taken before inference began, but executes in a physical state that has already drifted […]
Addressing the Reality Gap: A Three-Tension Framework for Agentic AI Adoption
arXiv:2604.27245v2 Announce Type: replace-cross Abstract: Generative AI has rapidly entered education through free consumer tools, outpacing the ability of schools and universities to respond. Now a new wave of more autonomous agentic AI systems–with the capacity to plan and act towards goals–promises both greater educational personalization and greater disruption. This chapter argues that successfully navigating […]
Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model
arXiv:2506.00286v3 Announce Type: replace-cross Abstract: We study risk-sensitive reinforcement learning in finite discounted MDPs with recursive entropic risk measures (ERM), where the risk parameter $beta neq 0$ controls the agent’s risk attitude: $beta>0$ for risk-averse and $beta<0$ for risk-seeking behavior. A generative model of the MDP is assumed to be available. Our focus is on […]
Multimodal system for skin cancer detection
arXiv:2601.14822v2 Announce Type: replace-cross Abstract: Melanoma detection is vital for early diagnosis and effective treatment. While deep learning models on dermoscopic images have shown promise, they require specialized equipment, limiting their use in broader clinical settings. This study introduces a multi-modal melanoma detection system using conventional photo images, making it more accessible and versatile. Our […]