Searcharxiv⌕ Search

arXiv subjects

Andrew Liu

Publications and source records attributed to Andrew Liu.

At least 19 recordsLinked to original sources

Offline KL-Regularized Reinforcement Learning with Stochastic Transitions

KL-regularized reinforcement learning is the objective behind RL fine-tuning of language models, and its data are often collected by the reference policy itself. However, beyond bandits and deterministic transitions, little is known about how much offline data it needs. In this work, we study finite discounted Markov decision processes with unknown stochastic transitions, $K$ state-action pairs and effective horizon $H$. For data that cover the regularized optimum with concentrability $C\geq 4$, every estimator needs $Ω(KCH^3/(ε\max\{ε,β\}))$ samples on some instances when $ε$ is small, where $β$ is the temperature. Under a fixed design, pessimistic soft value iteration with a variance-aware penalty attains this rate with high probability, up to logarithmic factors, when $β\geq 1.4H$. When the data come from the reference policy itself, we show that it covers the optimum up to a power law whose exponent grows as $H/β$; in the same temperature range, this power law alone gives the estimator a sample complexity polynomial in $1/ε$, with no coverage assumption. For $β\geq H$ the power can also increase the sample size needed by a factor polynomial in $1/ε$. Finally, the plug-in estimator, which is minimax optimal with a generative model, can fail on reference data at small temperatures when many actions are rarely seen, while the pessimistic estimator does not.

cs.LG↗

Sharp Sample Complexity of KL-Regularized Reinforcement Learning

KL-regularized reinforcement learning, the objective behind maximum-entropy RL and RL from human feedback, is variational inference in the graphical model of "control as inference": the regularized optimal policy is a posterior over trajectories, and the suboptimality of a policy is $β$ times a KL divergence between path measures. However, it is not known how many samples it takes to learn this posterior, even with a generative model. Earlier $1/ε$ guarantees scale with $H^5$ in the effective horizon $H$, and no lower bound for MDPs depends on the temperature $β$. In this work, we show that for a discounted MDP with $K$ state-action pairs, the plug-in estimator finds a policy that is $ε$-optimal from every initial state with $\widetilde{O}(KH^3/(ε\max\{ε,β\}) + KH)$ samples, and that no algorithm, even one that chooses where to sample, can do with fewer when $ε\lesssim \min\{H, H^2/β\}$. For $ε< β$ this is a $1/ε$ rate with the same horizon dependence as unregularized RL. We also find the exact asymptotic constant of the plug-in estimator, a Fisher-weighted variance of the estimated soft Q-function. The estimator is locally asymptotically minimax among methods that sample every pair equally often, and we give the allocation of samples that is optimal among adaptive designs. Simulations on small MDPs match the rates and the constants.

cs.LG↗

Explicit Regional Representations For Video Quality Assessment

End-to-end video quality assessment (VQA) methods leave the regional evidence underlying their predictions largely implicit. We introduce an explicit pixel-level regional representation for VQA, instantiated as a Quality-Relevance Heatmap (QRH) that combines localized degradation evidence with perceptual priors under vision-language model guidance, without requiring pixel-level annotations. We apply QRH to existing VQA models through two deterministic fragment-sampling strategies: distribution-preserving sampling approximates the original sampler's QRH-score distribution without retraining, while quality-aware sampling prioritizes regions with high QRH scores and is paired with fine-tuning. Experiments with DOVER on multiple benchmarks show that the former closely approximates predictions averaged over random samples, while the latter improves most evaluated metrics across popular VQA benchmarks. These results support explicit regional representations as a useful interface for downstream VQA.

cs.CV↗

The AI Theorist reveals excitonic structure in $α$-RuCl$_3$

Advances in experimental instrumentation and automation generate increasingly rich datasets, but turning experimental observations into microscopic understanding remains a bottleneck in scientific discovery. To accelerate this process, we introduce AI Theorist, a system of artificial intelligence (AI) agents for autonomous discovery of physical models through hypothesis generation, first-principles calculations and evidence-driven refinement. We apply the framework to $α$-RuCl$_3$, a leading candidate material for realizing a Kitaev quantum spin liquid, to investigate its electronic structure through optical spectra. AI Theorist develops a new interpretation of the optical and photocurrent observations, identifying distinct excitonic states with contrasting optical selection rules and real-space distributions. To our knowledge, this is the first demonstration of an AI system autonomously developing a physical model to explain previously unpublished experimental observations in a quantum material, utilizing first-principles electronic-structure and many-body calculations. Our results establish a route to autonomous theoretical discovery in materials science, in which AI agents use first-principles calculations to turn experimental observations into physical models and testable predictions.

cs.LG↗

Some Tokens Behave like Magnets: Revealing Linguistic Organization in the Layers of Language Models

We identify a special group of token vectors inside large language models (LLMs), which we term magnetic vectors, that organize the surrounding tokens by either attracting or repelling them. Particularly, tokens pointing the same way as an attracting magnet are elongated; tokens pointing the same way as a repelling magnet are compressed. Just as physical magnets pull or push away the iron filings around them, these vectors organize their surroundings through two opposing polarities. Moreover, we identify a statistically significant pattern in linguistic category where function words consistently act as repelling magnets in early layers, and we also find magnets consistently reorganize their polarities in unique ways deeper in the model. In a further case study we find this observation may unveil a deliberate, layer-wise organization in how LLMs process language. This pattern is consistent across different LLM architectures, sizes, and layer configurations. It is also causally relevant. When the LLM is fine-tuned for a downstream task, the task-functional tokens emerge as magnets. E.g., in question answering, the answer-span tokens become uniquely repelling magnets in the final layer, geometrically carving the answer out of the surrounding context. Furthermore, removing early-layer repelling magnets devastates syntactic tasks (POS tagging accuracy drops from 91% to below 10%) while sparing semantic ones, and removing late-layer attracting magnets does the reverse. We believe this phenomenon warrants further investigation, as it opens the first probe-free path to understanding how language models geometrically organize linguistic computation across their layers.

cs.CL↗

Non-linear Evolution of Dark Plasma Subhalos

Dark matter that self interacts through long-range forces exhibits coherent, collective effects that are absent in short-range interactions. In the case where dark matter interacts through a hidden-photon mediator, its dynamics closely resemble those of Standard Model plasmas. In such models, various astrophysical environments, including cluster collisions and subhalos orbiting their host halo, are susceptible to plasma instabilities: processes that modify the dark matter velocity distribution and lead to exponential growth of dark electromagnetic fields. In this paper, we present the first study of the non-linear evolution of electrostatic instabilities in dark matter subhalos orbiting within the Milky Way potential using a suite of particle-in-cell simulations. We find that the growth and saturation of these instabilities produce substantial turbulent heating and mass loss, with an efficiency that depends sensitively on subhalo mass and orbital eccentricity. For highly eccentric orbits, plasma heating can reduce the initial mass of a $10^7$ ($10^9$) $\text{M}_\odot$ subhalo by as much as $\sim 97\%$ ($\sim 84\%$) soon after first pericenter. Plasma-induced heating and stripping may therefore leave observable signatures in the Milky Way subhalo population, including a suppression of the low-mass subhalo mass function.

astro-ph.CO↗

ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution

The transition from sequential to parallel computing is essential for modern high-performance applications but is hindered by the steep learning curve of concurrent programming. This challenge is magnified for irregular data structures (such as sparse graphs, unbalanced trees, and non-uniform meshes) where static scheduling fails and data dependencies are unpredictable. Current Large Language Models (LLMs) often fail catastrophically on these tasks, generating code plagued by subtle race conditions, deadlocks, and sub-optimal scaling. We bridge this gap with ParEVO, a framework designed to synthesize high-performance parallel algorithms for irregular data. Our contributions include: (1) The Parlay-Instruct Corpus, a curated dataset of 13,820 tasks synthesized via a "Critic-Refine" pipeline that explicitly filters for empirically performant algorithms that effectively utilize Work-Span parallel primitives; (2) specialized DeepSeek, Qwen, and Gemini models fine-tuned to align probabilistic generation with the rigorous semantics of the ParlayLib library; and (3) an Evolutionary Coding Agent (ECA) that improves the "last mile" of correctness by iteratively repairing code using feedback from compilers, dynamic race detectors, and performance profilers. On the ParEval benchmark, ParEVO achieves an average 106x speedup (with a maximum of 1103x) across the suite, and a robust 13.6x speedup specifically on complex irregular graph problems, outperforming state-of-the-art commercial models. Furthermore, our evolutionary approach matches state-of-the-art expert human baselines, achieving up to a 4.1x speedup on specific highly-irregular kernels. Source code and datasets are available at https://github.com/WildAlg/ParEVO.

cs.LG↗

Diff2SP: Diffusion Models for Correlated Scenario Generation in Stochastic Programming

Scenario generation is a critical component in stochastic programming (SP), as it directly influences the quality of decision-making under uncertainty. Existing approaches predominantly rely on either sampling-based techniques or supervised learning using neural networks. Sampling-based techniques often struggle to capture complex dependencies and rare but plausible events, while supervised learning requires fixed input-output pairs for training and is limited in its ability to generate a wide variety of realistic scenarios that are not restricted by predefined patterns or rules. To address these limitations, we introduce Diff2SP, a diffusion-based generative framework that incorporates downstream optimization objectives directly into scenario generation. Unlike conventional methods that treat scenario generation and decision-making as separate steps, Diff2SP embeds stochastic optimization into the training process, enabling the generation of scenarios that are both statistically coherent and decision-aware. To formally justify this optimization-aware design, we establish a regret bounds that link distributional accuracy to decision quality, and establish sample complexity guarantees showing faster convergence than traditional generative models such as GANs. Empirical results on both synthetic and power-system datasets validate these theoretical insights, demonstrating that Diff2SP consistently improves both statistical fidelity and downstream optimization outcomes.

stat.CO↗

Relational reasoning and inductive bias in transformers and large language models

Transformer-based models have demonstrated remarkable reasoning abilities, but the mechanisms underlying relational reasoning remain poorly understood. We investigate how transformers perform \textit{transitive inference}, a classic relational reasoning behavior from psychology which elicits inference about indirectly related items (e.g., if $A > B$ and $B > C$, then $A > C$). We compare in-weights learning (IWL) and in-context learning (ICL) behaviors and mechanisms on these tasks, and fine profoundly different patterns of generalization. IWL models learn a linear embedding, which leads to transitive inference as well as other behavioral effects present in humans and animals. ICL models, in contrast, are capable of learning to generalize transitively, but only do so when it is necessitated by the training data, otherwise learning a match-and-copy strategy. Interestingly, pre-training ICL models on in-context linear regression tasks that provide them with a latent linear representation is sufficient to make the ICL behaviors and internal representations qualitatively and quantitatively more like IWL. In order to test whether the same inference patterns are present across in large language models, we leverage a congruency paradigm which allows us to differentially probe IWL and ICL generalization patterns without access to their training data. We indeed see IWL reasoning leads to more transitive generalization than ICL. Moreover, we find that prompting the ICL models to use a linear mental map led to increased transitive inference over different geometric prompts. Together, these results reveal that both the training regime and the geometric structure of induced representations critically determine transformers capacity for transitive inference.

cs.LG↗

OpenAI GPT-5 System Card

This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. This system card focuses primarily on gpt-5-thinking and gpt-5-main, while evaluations for other models are available in the appendix. The GPT-5 system not only outperforms previous models on benchmarks and answers questions more quickly, but -- more importantly -- is more useful for real-world queries. We've made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, and have leveled up GPT-5's performance in three of ChatGPT's most common uses: writing, coding, and health. All of the GPT-5 models additionally feature safe-completions, our latest approach to safety training to prevent disallowed content. Similarly to ChatGPT agent, we have decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards. While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm -- our defined threshold for High capability -- we have chosen to take a precautionary approach.

cs.CL↗

Structure Formation with Dark Magnetohydrodynamics

Long-range interactions in the dark sector can give rise to collective plasma phenomena that are capable of modifying the evolution of dark matter halos. We present the first study of gravitational collapse in a secluded dark $U(1)_D$ model using a magnetohydrodynamic description of the dark matter. We show that dark magnetic fields generate an anisotropic pressure that alters the Jeans scale and suppresses small-scale power in a direction-dependent manner. For a range of primordial magnetic spectral indices, this effect produces distinctive modifications to the linear matter power spectrum. We find that current observations cannot yet constrain viable dark magnetic fields, as CMB tensor modes mostly provide more stringent constraints. Nevertheless, forthcoming high-resolution probes of the matter power spectrum (CMB-HD lensing, HERA, and EDGES) will be able to test these predictions and are sensitive to dark charge-to-mass ratios in the range $10^{-20}\,\text{GeV}^{-1}\lesssim q_χ/m_χ\lesssim 10^{-14}\,\text{GeV}^{-1}$.

hep-ph↗

Privacy-Preserving Federated Fraud Detection in Payment Transactions with NVIDIA FLARE

Fraud-related financial losses continue to rise, while regulatory, privacy, and data-sovereignty constraints increasingly limit the feasibility of centralized fraud detection systems. Federated Learning (FL) has emerged as a promising paradigm for enabling collaborative model training across institutions without sharing raw transaction data. Yet, its practical effectiveness under realistic, non-IID financial data distributions remains insufficiently validated. In this work, we present a multi-institution, industry-oriented proof-of-concept study evaluating federated anomaly detection for payment transactions using the NVIDIA FLARE framework. We simulate a realistic federation of heterogeneous financial institutions, each observing distinct fraud typologies and operating under strict data isolation. Using a deep neural network trained via federated averaging (FedAvg), we demonstrate that federated models achieve a mean F1-score of 0.903 - substantially outperforming locally trained models (0.643) and closely approaching centralized training performance (0.925), while preserving full data sovereignty. We further analyze convergence behavior, showing that strong performance is achieved within 10 federated communication rounds, highlighting the operational viability of FL in latency- and cost-sensitive financial environments. To support deployment in regulated settings, we evaluate model interpretability using Shapley-based feature attribution and confirm that federated models rely on semantically coherent, domain-relevant decision signals. Finally, we incorporate sample-level differential privacy via DP-SGD and demonstrate favorable privacy-utility trade-offs...

cs.LG↗

3D Roadway Scene Object Detection with LIDARs in Snowfall Conditions

Because 3D structure of a roadway environment can be characterized directly by a Light Detection and Ranging (LiDAR) sensors, they can be used to obtain exceptional situational awareness for assitive and autonomous driving systems. Although LiDARs demonstrate good performance in clean and clear weather conditions, their performance significantly deteriorates in adverse weather conditions such as those involving atmospheric precipitation. This may render perception capabilities of autonomous systems that use LiDAR data in learning based models to perform object detection and ranging ineffective. While efforts have been made to enhance the accuracy of these models, the extent of signal degradation under various weather conditions remains largely not quantified. In this study, we focus on the performance of an automotive grade LiDAR in snowy conditions in order to develop a physics-based model that examines failure modes of a LiDAR sensor. Specifically, we investigated how the LiDAR signal attenuates with different snowfall rates and how snow particles near the source serve as small but efficient reflectors. Utilizing our model, we transform data from clear conditions to simulate snowy scenarios, enabling a comparison of our synthetic data with actual snowy conditions. Furthermore, we employ this synthetic data, representative of different snowfall rates, to explore the impact on a pre-trained object detection model, assessing its performance under varying levels of snowfall

cs.CV↗

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

Deep-Research agents, which integrate large language models (LLMs) with search tools, have shown success in improving the effectiveness of handling complex queries that require iterative search planning and reasoning over search results. Evaluations on current benchmarks like BrowseComp relies on black-box live web search APIs, have notable limitations in (1) fairness: dynamic and opaque web APIs hinder fair comparisons and reproducibility of deep research methods; (2) transparency: lack of control over the document corpus makes it difficult to isolate retriever contributions. In other words, the current evaluations may compare a complete deep research system at a given time, but they do not foster well-controlled experiments to provide insights into the capability of underlying deep research LLMs. To address these challenges, we introduce BrowseComp-Plus, a benchmark derived from BrowseComp, employing a fixed, carefully curated corpus. Each query in BrowseComp-Plus includes human-verified supporting documents and mined challenging negatives, enabling controlled experimentation. The benchmark is shown to be effective in distinguishing the performance of deep research systems. For instance, the open-source model Search-R1, when paired with the BM25 retriever, achieves 3.86% accuracy, whereas the GPT-5 achieves 55.9%. Integrating the GPT-5 with the Qwen3-Embedding-8B retriever further enhances its accuracy to 70.1% with fewer search calls. This benchmark allows comprehensive evaluation and disentangled analysis of deep research agents and retrieval methods, fostering insights into retrieval effectiveness, citation accuracy, and context engineering in Deep-Research system.

cs.CL↗

Flash Invariant Point Attention

Invariant Point Attention (IPA) is a key algorithm for geometry-aware modeling in structural biology, central to many protein and RNA models. However, its quadratic complexity limits the input sequence length. We introduce FlashIPA, a factorized reformulation of IPA that leverages hardware-efficient FlashAttention to achieve linear scaling in GPU memory and wall-clock time with sequence length. FlashIPA matches or exceeds standard IPA performance while substantially reducing computational costs. FlashIPA extends training to previously unattainable lengths, and we demonstrate this by re-training generative models without length restrictions and generating structures of thousands of residues. FlashIPA is available at https://github.com/flagshippioneering/flash_ipa.

cs.LG↗

FedFetch: Faster Federated Learning with Adaptive Downstream Prefetching

Federated learning (FL) is a machine learning paradigm that facilitates massively distributed model training with end-user data on edge devices directed by a central server. However, the large number of heterogeneous clients in FL deployments leads to a communication bottleneck between the server and the clients. This bottleneck is made worse by straggling clients, any one of which will further slow down training. To tackle these challenges, researchers have proposed techniques like client sampling and update compression. These techniques work well in isolation but combine poorly in the downstream, server-to-client direction. This is because unselected clients have outdated local model states and need to synchronize these states with the server first. We introduce FedFetch, a strategy to mitigate the download time overhead caused by combining client sampling and compression techniques. FedFetch achieves this with an efficient prefetch schedule for clients to prefetch model states multiple rounds before a stated training round. We empirically show that adding FedFetch to communication efficient FL techniques reduces end-to-end training time by 1.26$\times$ and download time by 4.49$\times$ across compression techniques with heterogeneous client settings. Our implementation is available at https://github.com/DistributedML/FedFetch

cs.LG↗

Bio2Token: All-atom tokenization of any biomolecular structure with Mamba

Efficient encoding and representation of large 3D molecular structures with high fidelity is critical for biomolecular design applications. Despite this, many representation learning approaches restrict themselves to modeling smaller systems or use coarse-grained approximations of the systems, for example modeling proteins at the resolution of amino acid residues rather than at the level of individual atoms. To address this, we develop quantized auto-encoders that learn atom-level tokenizations of complete proteins, RNA and small molecule structures with reconstruction accuracies well below 1 Angstrom. We demonstrate that a simple Mamba state space model architecture is efficient compared to an SE(3)-invariant IPA architecture, reaches competitive accuracies and can scale to systems with almost 100,000 atoms. The learned structure tokens of bio2token may serve as the input for all-atom generative models in the future.

cs.LG↗

A Role of Environmental Complexity on Representation Learning in Deep Reinforcement Learning Agents

We developed a simulated environment to train deep reinforcement learning agents on a shortcut usage navigation task, motivated by the Dual Solutions Paradigm test used for human navigators. We manipulated the frequency with which agents were exposed to a shortcut and a navigation cue, to investigate how these factors influence shortcut usage development. We find that all agents rapidly achieve optimal performance in closed shortcut trials once initial learning starts. However, their navigation speed and shortcut usage when it is open happen faster in agents with higher shortcut exposure. Analysis of the agents' artificial neural networks activity revealed that frequent presentation of a cue initially resulted in better encoding of the cue in the activity of individual nodes, compared to agents who encountered the cue less often. However, stronger cue representations were ultimately formed through the use of the cue in the context of navigation planning, rather than simply through exposure. We found that in all agents, spatial representations develop early in training and subsequently stabilize before navigation strategies fully develop, suggesting that having spatially consistent activations is necessary for basic navigation, but insufficient for advanced strategies. Further, using new analysis techniques, we found that the planned trajectory rather than the agent's immediate location is encoded in the agent's networks. Moreover, the encoding is represented at the population rather than the individual node level. These techniques could have broader applications in studying neural activity across populations of neurons or network nodes beyond individual activity patterns.

cs.LG↗