arXiv:2510.06062v2 Announce Type: replace
Abstract: Reinforcement learning (RL) has shown great promise in large language models (LLMs) post-training, which typically rely on token-level clipping to maintain stability during optimization. Despite the empirical success of GRPO-style methods, we identify a fundamental and previously overlooked challenge in this popular Outcome-Supervised RL (OSRL) paradigm. We reveal that in OSRL, where advantages are shared across tokens within a response, importance sampling (IS) ratios deviate from their traditional purpose of distribution correction as in classic RL, which become token-level weights that allocate the shared advantage signal across tokens. We show that this hidden role shift induces a critical mismatch for positive-advantage tokens, leading to unbalanced token weighting between positive and negative tokens. Specifically, it suppresses the update of underrepresented tokens that are lagging behind, while over-amplifying already high-probability tokens. This mismatch results in rich-get-richer dynamics that over-reinforce confident tokens, weaken catch-up learning that drive entropy collapse, excessive repetition, and premature convergence. To address this, we propose Asymmetric Importance Sampling Policy Optimization (ASPO), a simple yet effective strategy that reverses the ratio-induced weighting of positive-advantage tokens, while stabilizing extreme updates and maintaining gradient flow. This mismatch correction aligns their update direction with the learning dynamics of negative ones. Comprehensive experiments across math reasoning and coding benchmarks demonstrate that ASPO significantly mitigates entropy collapse, improves training stability, and enhances performance over strong GRPO-based baselines. Our analysis provides new insights into the role of token-level weighting in OSRL and highlights the critical importance of correcting ratio-induced weighting in LLM RL.
Science Journals
Beyond the Training Data: Confidence-Guided Mixing of Parameterizations in a Hybrid AI-Climate Model
arXiv:2510.08107v5 Announce Type: replace
Abstract: Persistent systematic errors in Earth system models (ESMs) arise from difficulties in representing the full diversity of subgrid, multiscale atmospheric convection and turbulence. Machine learning (ML) parameterizations trained on short high-resolution simulations show strong potential to reduce these errors. However, stable long-term atmospheric simulations with hybrid (physics + ML) ESMs remain difficult, as neural networks (NNs) trained offline often destabilize online runs. Training convection parameterizations directly on coarse-grained data is challenging, notably because scales cannot be cleanly separated. This issue is mitigated using data from superparameterized simulations, which provide clearer scale separation. Yet, transferring a parameterization from one ESM to another remains difficult due to distribution shifts that induce large inference errors. Here, we present a proof-of-concept where a ClimSim-trained, physics-informed NN convection parameterization is successfully transferred to ICON-A. The scheme is (a) trained on adjusted ClimSim data with subtracted radiative tendencies, and (b) integrated into ICON-A. The NN parameterization predicts its own error, enabling mixing with a conventional convection scheme when confidence is low, thus making the hybrid AI-physics model tunable with respect to observations and reanalysis through mixing parameters. This improves process understanding by constraining convective tendencies across column water vapor, lower-tropospheric stability, and geographical conditions, yielding interpretable regime behavior. In AMIP-style setups, several hybrid configurations outperform the default convection scheme (e.g., improved precipitation statistics). With additive input noise during training, both hybrid and pure-ML schemes lead to stable simulations and remain physically consistent for at least 20 years.
arXiv:2511.04484v2 Announce Type: replace
Abstract: We study the repeated optimal stopping problem, in which the same optimal stopping instance with an unknown distribution is solved repeatedly over $T$ rounds. We aim to simultaneously achieve strong per-round performance guarantees relative to a given baseline and sublinear regret across all rounds.
Our primary contribution is a comprehensive theoretical characterization of whether and when these two objectives are compatible. First, under standard semi-bandit feedback, we prove that maintaining the per-round guarantee forces regret of $\Omega(T / \log T)$. Second, even under full feedback, we show that requiring almost-sure satisfaction of the per-round guarantee in every round is incompatible with sublinear regret. Third, under full feedback, we propose a general algorithmic framework that achieves both sublinear regret and the per-round guarantee with high probability.
Our framework applies to canonical problems, including the prophet inequality, the secretary problem, and their variants under adversarial, random, and i.i.d. input models. For example, in the repeated prophet inequality problem, our method guarantees that, with high probability in each round, its expected reward is at least that of the classical single-sample algorithm, which achieves a $1/2$ competitive ratio, while simultaneously ensuring $\tilde{O}(\sqrt{T})$ regret.
Furthermore, we establish a regret lower bound of $\Omega(\sqrt{T})$ even in the i.i.d. model, which is nearly tight with respect to the number of rounds.
arXiv:2511.08103v4 Announce Type: replace
Abstract: Highly correlated photon sources can be realized through cooperative coupling among quantum systems, giving rise to superradiant collective emission. In solid-state ensembles, however, such collective behaviour is confined to subwavelength dimensions and is strongly suppressed at room temperature by inhomogeneous broadening and rapid dephasing, limiting practical implementations. Here, we show that molecular J-aggregates sustain room temperature superradiant emission and enter a highly collective regime when strongly coupled to delocalized photonic modes of a silicon bound-state-in-the-continuum (BIC) metasurface, extending J-exciton interactions far beyond the subwavelength limit. This enhanced cooperativity produces a photonic-fraction-dependent increase in emission rate and intensity and drives the system into a highly superbunched photon emission regime with g^((2))(0)>13. Spatial coherence measurements and stochastic modelling reveal that metasurface-mediated synchronization of ~10^3 J-excitons occurs within coupled superradiant domains spanning up to 6.7 um in diameter, corresponding to a 50-fold increase in inter-aggregate cooperative distance. These results establish exciton-polaritons in resonant dielectric metasurfaces as a platform to enhance superradiant emission and engineer temporally correlated light sources with picosecond-scale emission dynamics operating at room temperature.
arXiv:2511.18127v2 Announce Type: replace
Abstract: Real-time 3D hand forecasting is a critical component for fluid human-computer interaction in applications like AR and assistive robotics. However, existing methods are ill-suited for these scenarios, as they typically require offline access to accumulated video sequences and cannot incorporate language guidance that conveys task intent. To overcome these limitations, we introduce SFHand, the first streaming framework for language-guided 3D hand forecasting. SFHand autoregressively predicts a comprehensive set of future 3D hand states, including hand type, 2D bounding box, 3D pose, and trajectory, from a continuous stream of video and language instructions. Our framework combines a streaming autoregressive architecture with an ROI-enhanced memory layer, capturing temporal context while focusing on salient hand-centric regions. To enable this research, we also introduce EgoHaFL, the first large-scale dataset featuring synchronized 3D hand poses and language instructions. We demonstrate that SFHand achieves new state-of-the-art results in 3D hand forecasting, outperforming prior work by a significant margin of up to 35.8%. Furthermore, we show the practical utility of our learned representations by transferring them to downstream embodied manipulation tasks, improving task success rates by up to 13.4% on multiple benchmarks. Dataset page: https://huggingface.co/datasets/ut-vision/EgoHaFL, project page: https://github.com/ut-vision/SFHand.
arXiv:2511.18225v2 Announce Type: replace
Abstract: Quantum machine learning seeks to leverage quantum computers to improve upon classical machine learning algorithms. Currently, robust uncertainty quantification methods remain underdeveloped in the quantum domain, despite the critical need for reliable and trustworthy predictions. Recent work has introduced quantum conformal prediction, a framework that produces prediction sets that are guaranteed to contain the true outcome with a user-specified probability. In this work, we formalise how the time-varying noise inherent in quantum processors can undermine conformal guarantees, even when calibration and test data are exchangeable. To address this challenge, we draw on Adaptive Conformal Inference, a method which maintains validity over time via repeated recalibration. We introduce Adaptive Quantum Conformal Prediction (AQCP), an algorithm which provides asymptotic average coverage guarantees under arbitrary hardware noise conditions. Empirical studies on an IBM quantum processor demonstrate that AQCP achieves the target coverage level and exhibits greater stability than quantum conformal prediction.
arXiv:2511.19399v3 Announce Type: replace
Abstract: Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via reinforcement learning with verifiable rewards, which does not extend to realistic long-form tasks. We address this with Reinforcement Learning with Evolving Rubrics (RLER), where rubrics are constructed and maintained to co-evolve with the policy model during training. This allows the rubrics to incorporate newly explored information from search and contrasting model responses, enabling better fact checking and more discriminative on-policy feedback. Using RLER, we develop Deep Research Tulu (DR Tulu-8B), the first fully open model that is directly trained for open-ended, long-form deep research. Across four long-form deep research benchmarks in science, healthcare, and general domains, DR Tulu substantially outperforms existing open deep research agents (by 15.6% over Tongyi DR on average) and matches or exceeds proprietary deep research agents (by 0.7% over OpenAI DR on average), while being significantly smaller and cheaper per query (1000x cheaper than OpenAI DR per query).
arXiv:2511.21277v3 Announce Type: replace
Abstract: This paper presents LatencyScope, a mathematical framework for computing one-way uplink and downlink latency in fifth-generation radio access networks across diverse system configurations. LatencyScope models latency sources across the protocol stack, including radio interfaces, scheduling decisions, processing delays, frame structures, and hardware and software constraints, while capturing dependencies among configuration parameters and stochastic sources of delay. The framework also includes a configuration analyzer that uses these models to search billions of candidate settings and identify those that satisfy latency-reliability targets under user-specified constraints. We validate LatencyScope on two open-source fifth-generation radio access network testbeds, as well as on measurements from a public commercial fifth-generation network. The results show that LatencyScope closely matches empirical latency distributions, captures observed lower and upper latency bounds, and substantially outperforms prior analytical models and widely used fifth-generation network simulators. LatencyScope can determine whether ultra-reliable low-latency communication targets are feasible for a given deployment and, when they are feasible, efficiently find satisfying configurations, helping network operators reason about latency modeling, configuration analysis, and system-level bottlenecks.
arXiv:2605.15227v1 Announce Type: new
Abstract: Self-driving laboratories (SDLs) have attracted increasing attention as a means of accelerating scientific discovery; however, developing SDL software remains technically demanding. To improve accessibility, orchestration software frameworks have been proposed to coordinate SDL components. Nevertheless, existing frameworks are primarily designed for human interaction and do not provide standardized interfaces suitable for AI agents. In this work, we propose an SDL software architecture based on the Model Context Protocol (MCP), in which all SDL functionalities are exposed through MCP servers. Following this design principle, we introduce an MCP-based SDL orchestrator, named NIMO Controller. It provides a visual programming interface automatically generated through MCP-based tool discovery, allowing human users to design experimental workflows without writing code. The same MCP backend can also be accessed by AI agents, providing a unified interface for both human users and AI agents. We demonstrate the proposed system through a case study on a color-matching SDL. The results validate the usability of the proposed MCP-based SDL architecture.
arXiv:2605.15228v1 Announce Type: new
Abstract: Modern cloud and enterprise systems rely on identity-centric authorization, assuming that callers possessing valid credentials are safe to execute commands. The emergence of autonomous AI agents invalidates this assumption: agents can generate syntactically valid but semantically unsafe actions, making standing privileges a significant operational risk. This risk becomes especially acute in sovereign AI systems, where autonomous agents may interact with cloud infrastructure, regulated data, financial workflows, and national-scale digital services. Governed mutation substrates reduce this risk by interposing on agent actions: agents submit intents, infrastructure evaluates context and policy, and execution is mediated. However, this shifts the trust boundary: how can the decision to authorize an intent be made verifiable, distributed, and replayable?
We introduce a Distributed Trust Framework (DTF), a verification framework for governed mutation systems that computes execution authority from structured, verifiable artifacts. DTF introduces a Justification Proof to encode the admissibility basis of an action, a consensus model for independent evaluation, an ephemeral Execution Identity derived from the approved proof, and an append-only Evidence Chain that preserves the authorization lifecycle. Under stated substrate assumptions, this architecture enforces a compact authorization invariant: no high-stakes execution without a proof object, no derived authority without consensus, and no valid mutation detached from evidence.
We define the model, instantiate it over an OpenKedge-based governed mutation substrate, and show how it maps onto cloud-native environments. By shifting authorization from standing identity to proof-derived authority, DTF provides an infrastructure foundation for making agentic execution governable, auditable, and bounded in sovereign AI deployments.
arXiv:2603.01290v3 Announce Type: replace
Abstract: The 2026 Formula 1 technical regulations introduce a fundamental change to energy strategy: under a 50/50 internal combustion engine / battery power split with unlimited regeneration and a driver-controlled Override Mode, the optimal energy deployment policy depends not only on a driver's own state but on the hidden state of rival cars. This creates a Partially Observable Stochastic Game that cannot be solved by single-agent optimisation methods.
We present a tractable two-layer inference and decision framework. The first layer is a 40-state Hidden Markov Model (HMM) that infers a probability distribution over each rival's ERS charge level (four modes: H, M, L_harvest, L_derate), Override Mode status, and tyre degradation state from six publicly observable telemetry signals. The second layer is a Deep Q-Network (DQN) policy that takes the HMM belief state as input and selects between energy deployment strategies. We formally characterise the counter-harvest trap, a deceptive strategy in which a car deliberately suppresses observable deployment signals to induce a rival into a failed attack, and show that detecting it requires belief-state inference over both ERS level and the harvest/derate sub-mode.
On synthetic races, the HMM achieves 96.8% ERS-level accuracy (random baseline 25%), classifies L_harvest vs. L_derate with 89.4% accuracy, and detects counter-harvest trap conditions with 96.3% recall. Pre-season analysis indicates circuit-dependent recharge availability (1.0x to 2.2x per lap) as the primary confound; Melbourne is the hardest-case validation environment. Baum-Welch calibration on 2026 race telemetry begins with the Australian Grand Prix (8 March 2026).
arXiv:2605.15285v1 Announce Type: new
Abstract: Derivative-Informed Operator Learning (DIOL), i.e. learning a (nonlinear) operator and its derivatives, is an open research frontier at the foundations of the influential field of Operator Learning (OL). In particular, Universal Approximation Theorems (UATs) of nonlinear operators and their derivatives are foundational open questions and delicate problems in nonlinear functional analysis. In this manuscript, we prove the first UATs of non-linear $k$-times differentiable operators between Banach spaces and their derivatives, uniformly on compact sets and in weighted Sobolev norms for general finite input measures, via OL architectures. Our results are the first complete generalizations of the corresponding influential classical results in [Hornik, 1991] to infinite-dimensional settings and OL.
We discuss several open areas where DIOL and our UATs find applications: high-order accuracy in OL, fast constrained optimization in Banach spaces (e.g. optimal control of PDEs, inverse problems) and numerical methods for infinite-dimensional PDEs (e.g. HJB PDEs on Banach spaces from optimal control of PDEs, SPDEs, path-dependent systems, partially observed systems, mean-field control).
We parameterize nonlinear operators via Encoder-Decoder Architectures, renowned classes in OL due to their generality, including classical architectures, such as DeepONets, Deep-H-ONets, PCA-Nets. Our results are based on four key features that allow us to prove UATs in full generality: (i) Approximation Properties of Banach spaces. (ii) $k$-times continuous differentiability in the sense of Bastiani (weaker than $k$-times continuous Fr\'echet differentiability). (iii) Natural compact-open topologies for UA; indeed, we show that UA in standard compact-open topologies induced by operator norms is violated even for Fr\'echet derivatives. (iv) Construction of novel weighted Sobolev spaces for the UA.
arXiv:2605.15232v1 Announce Type: new
Abstract: Test Suite Minimization (TSM) reduces the size of test suites while preserving their fault detection capability. In black-box TSM, reduction is performed without analyzing production code. While several black-box TSM approaches have explored metrics like test logs or test similarity, those often suffer from scalability and efficiency issues. On the other hand, change-proneness (CP), recently emerged as an efficient and scalable alternative metric, has only been applied at class level. To accurately identify fault-revealing test cases, we propose CP at finer-grained method-level and implement Method-level Change-proneness based Test-suite Minimization (MCTM). MCTM first calculates CP for each method from version control metadata, then determines the dependency between test cases and methods by analyzing the test-code call-graph. Next, it scores the association between test cases and their invoked methods using statistical measures such as Average, Geometric Mean etc. Finally, test cases with the highest scores are selected to form the reduced suite. Evaluation on 15 open-source Java projects with 635 buggy versions shows MCTM achieves 0.93 accuracy and 0.94 fault detection rate on average, significantly outperforming class-level CP and similarity-based approaches while maintaining superior efficiency.
arXiv:2605.16233v1 Announce Type: new
Abstract: Can LLM agents improve decision-making through self-generated memory without gradient updates? We propose FORGE (Failure-Optimized Reflective Graduation and Evolution), a staged, population-based protocol that evolves prompt-injected natural-language memory for hierarchical ReAct agents. FORGE wraps a Reflexion-style inner loop, where a dedicated reflection agent (using the same underlying LLM, no distillation from a stronger model) converts failed trajectories into reusable knowledge artifacts: textual heuristics (Rules), few-shot demonstrations (Examples), or both (Mixed), with an outer loop that propagates the best-performing instance's memory to the population between stages and freezes converged instances via a graduation criterion. We evaluate on CybORG CAGE-2, a stochastic network-defense POMDP at a 30-step horizon against the B-line attacker, where all four tested LLM families (Gemini-2.5-Flash-Lite, Grok-4-Fast, Llama-4-Maverick, Qwen3-235B) exhibit strongly negative, heavy-tailed zero-shot rewards. Compared against both a zero-shot baseline and a Reflexion baseline (isolated single-stream learning), FORGE improves average evaluation return by 1.7-7.7$\times$ over zero-shot and by 29-72% over Reflexion in all 12 model-representation conditions, reducing major-failure rates (below $-100$) to as low as $\sim$1%. We find that (1) population broadcast is critical mechanism, with a no-graduation ablation confirming that broadcast carries the performance gains while graduation primarily saves compute; (2) Examples achieves the strongest returns for three of four models, Rules offers the best cost-reliability profile with $\sim$40% fewer tokens; and (3) weaker baseline models benefit disproportionately, suggesting FORGE may mitigate capability gaps rather than amplify strong models. All evidence is confined to CAGE-2 B-line; cross-family findings are directional evidence.
arXiv:2605.15234v1 Announce Type: new
Abstract: Many complex systems can be reduced to their key components through spectrally decomposing matrices that capture their dynamics. These matrices can in turn be constructed from data, often by least-squares fitting: examples of algorithms to do this include Dynamical Mode Decomposition and variants, subspace identification and eigenvalue realisation algorithms. Typical outputs of these algorithms include a range of isolated, peripheral eigenvalues capturing persistent emergent patterns in the system. However, there is no objective way to assess which of these discrete eigenvalues are artefacts of finite data error, and which are reflections of a fully sampled operator.
n this paper, we present a sampling pseudospectrum $P(\lambda)$, that provides probabilistic information on the behaviour of finite-data eigenvalues in the complex plane, and an estimator $\hat P(\lambda)$, which can be obtained by reprocessing our finite data sample. The estimator, which is computationally efficient to implement, allows us to test statistically for the location of the true eigenvalues. This gives us a rigorous and very general way to assess whether the patterns we extract from finite data are likely to be signal or noise.
arXiv:2603.18221v2 Announce Type: replace
Abstract: Students in our AI/ML course submitted polished, well-argued project analyses. Then, in class discussion, we asked them to walk through a single choice from their own work. Many could not. The writing looked great. The understanding often wasn't. Oral examinations retain an evidentiary link where written work no longer does: a student who can reason aloud, defend a decision under follow-up, and adapt when pushed demonstrates something no submitted document can certify. The obstacle has always been cost. A 25-minute oral reviewed by two graders takes roughly 30 combined instructor and TA hours for 36 students; at 100 the format is untenable. Voice AI and automated grading change the arithmetic. We built Viva, a system that conducts a personalized oral exam, then grades the transcript with a panel of three LLMs that score independently, read each other's assessments, and revise. Across two undergraduate cohorts at NYU Stern (36 students in Fall 2025, 37 in Spring 2026), grading-LLM cost stayed under one dollar per exam within the ElevenLabs subscription covering our voice minutes; for deployments exceeding an equivalent credit pool, budget about a dollar per ten minutes of graded exam time, practical for weekly assignments, not just finals. The system also broke instructively: the agent asked several questions at once, failed to randomize topics across the cohort, and a voice cloned from the professor's came across as harsh, replaced in Spring 2026 with a calm preset. These failures, with an earlier finding that a monolithic agent handling both examination and grading proved unreliable, point to five candidate transferable patterns: decompose into single-purpose modules, constrain behavior with code rather than prompts, keep randomization out of the LLM, grade with a multi-model panel whose members disagree, and choose voice characteristics with the same care as question design.
arXiv:2605.15288v1 Announce Type: new
Abstract: The Electron-Ion Collider (EIC) is a next-generation particle accelerator facility designed to probe the fundamental structure of matter such as the origins of nucleon mass, spin, and the dynamic behavior of quarks and gluons within nucleon and nucleus. As the electromagnetic calorimeter in the barrel region, the Barrel Imaging Calorimeter (BIC) is tasked with precise energy measurements of electrons and photons as well as efficient separation of these particles from background pions. The BIC integrates Pb/SciFi sampling layers and AstroPix silicon pixel sensors for three-dimensional shower imaging. The Korean group has actively contributed through silicon chip testing, module assembly, prototype development, beam test, readout system design, and detailed simulations. This presentation highlights the recent progress and plans for the R\&D of the Barrel Imaging Calorimeter in Korea.
arXiv:2601.21798v2 Announce Type: replace
Abstract: Large Language Models(LLMs) have revolutionized text generation and multimodal perception,but their capabilities in 3D content generation remain underexplored. Existing methods compromise by producing either low-resolution meshes or coarse structural proxies, failing to capture finegrained geometry natively. In this paper, we propose CG-MLLM, a novel Multi-modal Large Language Model (MLLM) capable of 3D captioning and high-resolution 3D generation in a single framework. Leveraging the Mixture-ofTransformer architecture, CG-MLLM decouples disparate modeling needs, where the Token-level Autoregressive (TokenAR) Transformer handles token-level content, and the Block-level Autoregressive (BlockAR) Transformer handles blocklevel content. By integrating a pre-trained visionlanguage backbone with a specialized 3D VAE latent space, CG-MLLM facilitates long-context interactions between standard tokens and spatial blocks within a single integrated architecture. Experimental results show that CG-MLLM significantly outperforms existing MLLMs in generating high-fidelity 3D objects, effectively bringing high-resolution 3D content creation into the mainstream LLM paradigm. Beyond generation, we further observe that learning to produce 3D content transfers back to perception, strengthening the model's image-based 3D understanding.
arXiv:2601.23068v2 Announce Type: replace
Abstract: Computing the importance of features in supervised classification tasks is critical for model interpretability. Shapley values are a widely used approach for explaining model predictions, but require direct access to the underlying model, an assumption frequently violated in real-world deployments. We investigate whether meaningful feature attributions can be obtained in a zero-shot setting, using only the input data distribution and no evaluations of the target model. Because multiple models can produce identical predictions yet yield different Shapley decompositions, the mapping from data to attributions is not uniquely identifiable. We therefore target attributions that are "true to the data" rather than "true to the model", learning a posterior mean attribution under a meta-training prior. To this end, we introduce ExplainerPFN, a tabular foundation model built on TabPFN, pretrained on synthetic structural causal datasets supervised with exact or near-exact Shapley values, that predicts feature attributions for unseen tabular datasets without model access, gradients, or example explanations.
Our contributions are fourfold: (1) we show that few-shot surrogate explainers achieve high SHAP fidelity with as few as two reference observations; (2) we propose ExplainerPFN, the first zero-shot method for estimating Shapley-value-style feature attributions without access to the underlying model or reference explanations, providing a principled attribution where no existing explainer can be applied; (3) we release an open-source implementation including the full training pipeline and synthetic data generator; and (4) through extensive experiments on real and synthetic datasets, we show that ExplainerPFN achieves performance competitive with few-shot surrogate explainers that rely on 2-10 SHAP examples.
arXiv:2605.15507v1 Announce Type: new
Abstract: For a Gaussian source under mean-squared error (MSE), classical transform coding is rate--distortion (RD) optimal: the Karhunen--Loeve transform (KLT) diagonalizes the covariance, reverse waterfilling allocates the bits, and scalar quantization closes the loop. This elegant story breaks down for multimodal sources, where no single covariance can capture heterogeneous local geometries, and the RD function loses its closed form. We revisit this problem through Gaussian-mixture sources and develop a constructive RD theory for them. Our key finding is that the mixture structure incurs only a component label cost. Conditioned on the active mixture component, each branch is Gaussian; the challenge is allocating bits across heterogeneous branches. We prove that the genie-aided conditional RD function is governed by a single global reverse-waterfilling level shared across all components and eigenmodes. Building on this result, we introduce PrismQuant, which transmits the component label losslessly and encodes the residual using the component-matched KLT, followed by scalar quantization, achieving a rate of H(C)/n bits per source dimension of the converse, with a vanishing asymptotic gap. We further develop a practical implementation based on EM-driven Gaussian-mixture learning, component-adaptive KLTs, and entropy-constrained scalar quantization (ECSQ). Experiments on synthetic Gaussian mixtures show that PrismQuant closely approaches the theoretical RD bound, while experiments on real-world channel-state-information (CSI) data demonstrate competitive or superior performance compared with transformer-based learned codecs at more than one order of magnitude smaller model size.
arXiv:2512.08052v3 Announce Type: replace
Abstract: Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually, learning-based approaches have emerged as promising alternatives, most notably Deep Reinforcement Learning (DRL) and Deep Imitation Learning (DIL). DRL leverages reward signals to optimize behavior, while DIL uses expert demonstrations to guide learning. This document introduces DRL and DIL in the context of embodied agents, adopting a concise, depth-first approach to the literature. It is self-contained, presenting all necessary mathematical and machine learning concepts as they are needed. It is not intended as a survey of the field; rather, it focuses on a small set of foundational algorithms and techniques, prioritizing in-depth understanding over broad coverage. The material ranges from Markov Decision Processes to REINFORCE and Proximal Policy Optimization (PPO) for DRL, and from Behavioral Cloning to Dataset Aggregation (DAgger) and Generative Adversarial Imitation Learning (GAIL) for DIL.
arXiv:2505.19241v2 Announce Type: replace
Abstract: The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks, such as question answering, mathematical reasoning, and code generation. However, achieving effective LLM alignment depends on high-quality datasets of human preferences. Collecting these datasets requires human preference annotation, which is costly and resource-intensive, necessitating efficient active data selection methods. Existing methods either lack a strong theoretical foundation or depend on restrictive assumptions about the reward function, such as linear latent reward functions. To this end, we propose an algorithm, ActiveDPO, that uses a theoretically grounded data selection criterion for non-linear reward functions while directly leveraging the LLM itself to parameterize the reward model used for active data selection. As a result, ActiveDPO explicitly accounts for the LLM's influence on data selection, unlike methods that select data without considering the LLM that is being aligned, thereby leading to more effective and efficient data collection. Our extensive experiments demonstrate that ActiveDPO outperforms existing methods across various models and real-world preference datasets.
arXiv:2512.06655v3 Announce Type: replace
Abstract: Sparse autoencoders (SAEs) are increasingly used to extract activation directions for inference-time steering, but their standard sparsity objective treats latent features as independent. This prior can be poorly matched to high-level safety behaviors, where refusal and harmful compliance appear to depend on distributed structure in activation space. We introduce Graph-Regularized Sparse Autoencoders (GSAE), a dictionary-learning method that learns safety-steering directions by smoothing SAE decoder vectors over a neuron co-activation graph and applying the resulting direction bank through a two-gate runtime controller. Empirically, GSAE improves selective refusal across JailbreakBench, HarmBench, and XSTest, increasing harmful-request refusal while keeping benign-prompt refusals low. On Llama-3-8B, replacing the standard SAE with GSAE in an otherwise identical pipeline improves $\Delta_s$ by $20.1$ points on JailbreakBench and $16.8$ points on HarmBench. GSAE outperforms activation-steering baselines and black-box guardrails, preserves benign-task performance, generalizes across Llama-3, Mistral, Qwen 2.5, and Phi-4, and remains strong under black-box and gray-box jailbreak attacks.
arXiv:2605.07523v1 Announce Type: cross
Abstract: In the imprecise geometry model, the input is an imprecise point set, which is a family of regions $F = (R_1, \ldots,R_n)$, where for each $R_i$ one may retrieve the true point $p_i \in R_i$. By preprocessing $F$, we can construct the output, in our case the Pareto front, on $P$ faster.
We efficiently construct the Pareto front of an imprecise point set in the plane. Efficiency is interpreted in two ways: minimizing (i) the number of retrievals, and (ii) the computation time used to determine the set of regions that must be retrieved and to construct the Pareto front.
We present an algorithm to construct the Pareto front for possibly overlapping rectangles that is \emph{instance-optimal} with respect to the number of retrievals, meaning that for every fixed input $(F, P)$, there is no algorithm that retrieves asymptotically fewer regions to compute the output. This is a strong algorithmic quality, as it means that our algorithm is competitive even to clairvoyant algorithms which know a correct guess of the output and only have to verify its correctness. In terms of algorithmic running time, instance-optimality is provably unobtainable. We instead present an algorithm which is within a $\log n$-factor of instance-optimality. This generalizes earlier results to overlapping input regions, at only a minor cost in running time.
For unit squares, we present an algorithm that is not only instance-optimal in the number of retrievals, but also \emph{universally} optimal in terms of running time, meaning that for any fixed set of regions $F$, no algorithm has a better worst-case running time for all possible point sets $P$. This is the first universally optimal algorithm for overlapping planar input. Compared to previous work, this result improves the degree of overlap, the preprocessing time, the number of retrievals, and the running time.
arXiv:2605.15816v1 Announce Type: new
Abstract: Stipple patterns, point sets whose local density tracks a target image, are traditionally produced by per-density iterative optimizers, which are slow, non-differentiable, and must be re-run from scratch for each new target. Learned alternatives have so far addressed only unconditional point generation; capacity-constrained, image-conditioned stippling has remained out of reach. We present the first diffusion-based sampler that simultaneously satisfies a learned local point-distribution prior and a continuous, image-defined capacity constraint at inference. The method is a ControlNet branch built on top of an optimal-transport-grid point-set diffusion baseline, conditioned on the target density map and a high-resolution image. Two design choices make the combination tractable: training and inference are restricted to the late-stage denoising regime, initialized from a density-weighted rejection sample, and the standard zero-convolution injection is replaced with a sigmoid-gated 1x1 projection that preserves the base model's blue-noise structure under hard density signals. A single trained checkpoint accepts arbitrary target densities at inference, generalizes to point budgets that were not seen during training, and produces stipples in time nearly independent of the output point count. On the Icons-50 benchmark, our learned sampler reaches parity with per-density-optimized baselines on every reported metric while remaining differentiable end-to-end.