Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning
arXiv:2603.22292v1 Announce Type: new Abstract: Sequential decision making using Markov Decision Process underpins many realworld applications. Both model-based and model free methods have achieved strong results in these settings. However, real-world tasks must balance reward maximization with safety constraints, often...
Efficient Embedding-based Synthetic Data Generation for Complex Reasoning Tasks
arXiv:2603.22294v1 Announce Type: new Abstract: Synthetic Data Generation (SDG), leveraging Large Language Models (LLMs), has recently been recognized and broadly adopted as an effective approach to improve the performance of smaller but more resource and compute efficient LLMs through fine-tuning....
Mitigating Premature Discretization with Progressive Quantization for Robust Vector Tokenization
arXiv:2603.22304v1 Announce Type: new Abstract: Vector Quantization (VQ) has become the cornerstone of tokenization for many multimodal Large Language Models and diffusion synthesis. However, existing VQ paradigms suffer from a fundamental conflict: they enforce discretization before the encoder has captured...
Full waveform inversion method based on diffusion model
arXiv:2603.22307v1 Announce Type: new Abstract: Seismic full-waveform inversion is a core technology for obtaining high-resolution subsurface model parameters. However, its highly nonlinear characteristics and strong dependence on the initial model often lead to the inversion process getting trapped in local...
UniFluids: Unified Neural Operator Learning with Conditional Flow-matching
arXiv:2603.22309v1 Announce Type: new Abstract: Partial differential equation (PDE) simulation holds extensive significance in scientific research. Currently, the integration of deep neural networks to learn solution operators of PDEs has introduced great potential. In this paper, we present UniFluids, a...
ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography
arXiv:2603.22316v1 Announce Type: new Abstract: Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination, making it highly relevant to applications such as film production, gaming, and animation. Recent group dance generation models have achieved promising generation...
Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning
arXiv:2603.22317v1 Announce Type: new Abstract: Graph-structured data typically exhibits complex topological heterogeneity, making it difficult to model accurately within a single Riemannian manifold. While emerging mixed-curvature methods attempt to capture such diversity, they often rely on implicit, task-driven routing that...
A Multi-Task Targeted Learning Framework for Lithium-Ion Battery State-of-Health and Remaining Useful Life
arXiv:2603.22323v1 Announce Type: new Abstract: Accurately predicting the state-of-health (SOH) and remaining useful life (RUL) of lithium-ion batteries is crucial for ensuring the safe and efficient operation of electric vehicles while minimizing associated risks. However, current deep learning methods are...
DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression
arXiv:2603.22324v1 Announce Type: new Abstract: We introduce Delta-Aware Quantization (DAQ), a data-free post-training quantization framework that preserves the knowledge acquired during post-training. Standard quantization objectives minimize reconstruction error but are agnostic to the base model, allowing quantization noise to disproportionately...
Beyond the Mean: Distribution-Aware Loss Functions for Bimodal Regression
arXiv:2603.22328v1 Announce Type: new Abstract: Despite the strong predictive performance achieved by machine learning models across many application domains, assessing their trustworthiness through reliable estimates of predictive confidence remains a critical challenge. This issue arises in scenarios where the likelihood...
Cloud-Edge Collaborative Large Models for Robust Photovoltaic Power Forecasting
arXiv:2603.22343v1 Announce Type: new Abstract: Photovoltaic (PV) power forecasting in edge-enabled grids requires balancing forecasting accuracy, robustness under weather-driven distribution shifts, and strict latency constraints. Local specialized models are efficient for routine conditions but often degrade under rare ramp events...
COMPASS-Hedge: Learning Safely Without Knowing the World
arXiv:2603.22348v1 Announce Type: new Abstract: Online learning algorithms often faces a fundamental trilemma: balancing regret guarantees between adversarial and stochastic settings and providing baseline safety against a fixed comparator. While existing methods excel in one or two of these regimes,...
Unveiling the Mechanism of Continuous Representation Full-Waveform Inversion: A Wave Based Neural Tangent Kernel Framework
arXiv:2603.22362v1 Announce Type: new Abstract: Full-waveform inversion (FWI) estimates physical parameters in the wave equation from limited measurements and has been widely applied in geophysical exploration, medical imaging, and non-destructive testing. Conventional FWI methods are limited by their notorious sensitivity...
Three Creates All: You Only Sample 3 Steps
arXiv:2603.22375v1 Announce Type: new Abstract: Diffusion models deliver high-fidelity generation but remain slow at inference time due to many sequential network evaluations. We find that standard timestep conditioning becomes a key bottleneck for few-step sampling. Motivated by layer-dependent denoising dynamics,...
Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters
arXiv:2603.22379v1 Announce Type: new Abstract: Adapters are often selected and deployed based on nominal labels (e.g., instruction-tuned), which implicitly suggest what capability improves after adaptation. We test whether nominal training objectives reliably align with realized cross-task capability gains by evaluating...
Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure
arXiv:2603.22384v1 Announce Type: new Abstract: Autonomous agents operating in continuous environments must decide not only what to do, but when to act. We introduce a lightweight adaptive temporal control system that learns the optimal interval between cognitive ticks from experience,...
Model Predictive Control with Differentiable World Models for Offline Reinforcement Learning
arXiv:2603.22430v1 Announce Type: new Abstract: Offline Reinforcement Learning (RL) aims to learn optimal policies from fixed offline datasets, without further interactions with the environment. Such methods train an offline policy (or value function), and apply it at inference time without...
SkillRouter: Retrieve-and-Rerank Skill Selection for LLM Agents at Scale
arXiv:2603.22455v1 Announce Type: new Abstract: As LLM agent ecosystems grow, the number of available skills (tools, plugins) has reached tens of thousands, making it infeasible to inject all skills into an agent's context. This creates a need for skill routing...
Adversarial Vulnerabilities in Neural Operator Digital Twins: Gradient-Free Attacks on Nuclear Thermal-Hydraulic Surrogates
arXiv:2603.22525v1 Announce Type: new Abstract: Operator learning models are rapidly emerging as the predictive core of digital twins for nuclear and energy systems, promising real-time field reconstruction from sparse sensor measurements. Yet their robustness to adversarial perturbations remains uncharacterized, a...
A Foundation Model for Instruction-Conditioned In-Context Time Series Tasks
arXiv:2603.22586v1 Announce Type: new Abstract: In-context learning (ICL) allows a model to adapt at inference time by conditioning on examples rather than updating parameters. Existing time-series foundation models use implicit positional context, retrieval, or task-specific objectives, but rarely explicit instruction-conditioned...
The 14th Amendment does not codify English principles of subjectship: A brief reply to the Amar brothers
Professors Akhil and Vikram Amar have responded to my recent post arguing that the 14th Amendment does not grant automatic citizenship to the children of temporary visitors to the United […]The postThe 14th Amendment does not codify English principles of...
Electronic Frontier Foundation to swap leaders as AI, ICE fights escalate
Public interest in government tech abuses is peaking. EFF's new leader plans to build on that.
Arm is releasing the first in-house chip in its 35-year history
Arm is producing its own CPU for the first time. It developed the CPU with Meta, which is also the chip's first customer.
Talat’s AI meeting notes stay on your machine, not in the cloud
The subscription-free AI meeting notes app is a local-first twist on notetaking tools like Granola.
Decentring the governance of AI in the military: a focus on the postcolonial subject
Abstract The governance of emerging technologies with increased autonomy in the military has become a topical issue in recent years, especially considering the rapid advances in artificial intelligence and related innovations in computer science. Despite this hype, the postcolonial subject’s...
Domain-Specialized Tree of Thought through Plug-and-Play Predictors
arXiv:2603.20267v1 Announce Type: new Abstract: While Large Language Models (LLMs) have advanced complex reasoning, prominent methods like the Tree of Thoughts (ToT) framework face a critical trade-off between exploration depth and computational efficiency. Existing ToT implementations often rely on heavyweight...
ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data Elicitation
arXiv:2603.21140v1 Announce Type: new Abstract: Training large language models (LLMs) with synthetic reasoning data has become a popular approach to enhancing their reasoning capabilities, while a key factor influencing the effectiveness of this paradigm is the quality of the generated...
DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation
arXiv:2603.20470v1 Announce Type: new Abstract: The rapid growth of the text-to-image (T2I) community has fostered a thriving online ecosystem of expert models, which are variants of pretrained diffusion models specialized for diverse generative abilities. Yet, existing model merging methods remain...
Me, Myself, and $\pi$ : Evaluating and Explaining LLM Introspection
arXiv:2603.20276v1 Announce Type: new Abstract: A hallmark of human intelligence is Introspection-the ability to assess and reason about one's own cognitive processes. Introspection has emerged as a promising but contested capability in large language models (LLMs). However, current evaluations often...