arXiv:2602.02556v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on external retrieval, which is similarity-based, can introduce noise, and adds latency. We introduce SEAM (Structured Experience Adapter Module), a lightweight, executor-specific plug-in that stores experience in its parameters and generates […]
Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing
arXiv:2604.24162v1 Announce Type: cross Abstract: Defending against backdoor attacks in large language models remains a critical practical challenge. Existing defenses mitigate these threats but typically incur high preparation costs and degrade utility via offline purification, or introduce severe latency via complex online interventions. To overcome this dichotomy, we present Tail-risk Intrinsic Geometric Smoothing (TIGS), a […]
Energy-Aware Routing to Large Reasoning Models
arXiv:2601.00823v2 Announce Type: replace Abstract: Large reasoning models (LRMs) have heterogeneous inference energy costs based on which model is used and how much it reasons. To reduce energy, it is important to choose the right LRM and operate it in the right way. As a result, the performance of systems that dispatch tasks to different […]
Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion
arXiv:2604.24351v1 Announce Type: cross Abstract: Controllable diffusion methods have substantially expanded the practical utility of diffusion models, but they are typically developed as isolated, backbone-specific systems with incompatible training pipelines, parameter formats, and runtime hooks. This fragmentation makes it difficult to reuse infrastructure across tasks, transfer capabilities across backbones, or compose multiple controls within a […]
Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data
arXiv:2604.24662v1 Announce Type: cross Abstract: Identifying the dynamical state variables of a system from high-dimensional observations is a central problem across physical sciences. The challenge is that the state variables are not directly observable and must be inferred from raw high-dimensional data without supervision. Here we introduce DySIB (Dynamical Symmetric Information Bottleneck) as a method […]
Isotonic Layer: A Unified Framework for Recommendation Calibration and Debiasing
arXiv:2603.06589v2 Announce Type: replace-cross Abstract: Model calibration and debiasing are fundamental yet operationally expensive challenges in large-scale recommendation systems. Existing approaches treat them as separate problems requiring distinct infrastructure: post-hoc calibration pipelines, propensity estimation workflows, and per-segment model farms. We introduce the Isotonic Layer, a differentiable piecewise linear module that unifies both problems within a […]
AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation
arXiv:2604.24086v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models have been demonstrated possessing strong zero-shot generalization for robot control, their massive parameter sizes typically necessitate cloud-based deployment. However, cloud deployment introduces network jitter and inference latency, which can induce severe spatiotemporal misalignment in mobile navigation under continuous displacement, so that the stale intents expressed in […]
Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech
arXiv:2510.05799v2 Announce Type: replace-cross Abstract: Aligning text-to-speech (TTS) system outputs with human feedback through preference optimization has been shown to effectively improve the robustness and naturalness of language model-based TTS models. Current approaches primarily require paired desirable and undesirable samples at the utterance level. However, such pairs are often limited in TTS output data, and […]
Verifying Quantized GNNs With Readout Is Decidable But Highly Intractable
arXiv:2510.08045v2 Announce Type: replace-cross Abstract: We introduce a logical language for reasoning about quantized aggregate-combine graph neural networks with global readout (ACR-GNNs). We provide a logical characterization and use it to prove that verification tasks for quantized GNNs with readout are (co)NEXPTIME-complete. This result implies that the verification of quantized GNNs is computationally intractable, prompting […]
Supervised Learning Has a Necessary Geometric Blind Spot: Theory, Consequences, and Minimal Repair
arXiv:2604.21395v2 Announce Type: replace-cross Abstract: PGD adversarial training, the standard robustness method, can reduce Jacobian Frobenius norm yet worsen clean-input geometry (e.g., TDI 1.336 vs. ERM 1.093). We show this is not an implementation artifact but a theorem-level consequence of supervised learning. We prove that any encoder minimizing supervised loss must retain non-zero sensitivity along […]
AgenticCache: Cache-Driven Asynchronous Planning for Embodied AI Agents
arXiv:2604.24039v1 Announce Type: cross Abstract: Embodied AI agents increasingly rely on large language models (LLMs) for planning, yet per-step LLM calls impose severe latency and cost. In this paper, we show that embodied tasks exhibit strong plan locality, where the next plan is largely predictable from the current one. Building on this, we introduce AgenticCache, […]
End-to-End Learning for Partially-Observed Time Series with PyPOTS
arXiv:2604.24041v1 Announce Type: cross Abstract: Partially-observed time series (POTS) is ubiquitous in real-world applications, yet most existing toolchains separate missing-value handling from downstream learning, which limits reproducibility and overall performance. This tutorial introduces PyPOTS, an open-source Python ecosystem for end-to-end data mining and machine learning on POTS. We present practical workflows spanning missingness simulation, data […]