Searcharxiv⌕ Search

arXiv subjects

Yu Yao

Publications and source records attributed to Yu Yao.

At least 19 recordsLinked to original sources
arXiv2026

NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale

Agentic reinforcement learning (RL) disaggregates training from rollout into different clusters, so each policy update must reach rollout clusters before the next batch: a full 1T checkpoint takes 87.5 min between two AWS regions, yet only 1-2% of BF16 elements change their stored values per step. Concurrent systems use this sparsity but reimplement placement rules, assemble full tensors, rebuild values arithmetically, or rely on a cross-cluster collective, and none fully recovers from mid-refit failures. We present NeMo-DCR (Delta-Compressed Refit), which sends only changes yet gives receivers the bits of a dense refit. NeMo-DCR describes changes in the Hugging Face canonical coordinates that both sides already share and leaves their placement to the serving runtime's native loader. It projects over 96% of MoE weight bytes directly and converts the rest, under 4%. It encodes changes as compressible XOR masks for over 96% of these bytes and as overwrites where XOR masks cannot apply, streams them over object storage or a relay tree without a cross-cluster collective, and updates receivers in place, recovering from failures with overwrite retries and a joint commit. With real updates, NeMo-DCR is $7\times$ faster than AReaL-DTE. In 3% and 5% stress cases, 30B-1T refits are 12-40$\times$ faster than a transport-only full-checkpoint reference over the same object storage, and would make a synchronous Kimi K2 RL step 1.4-1.5$\times$ faster at 1T.

cs.DC↗
arXiv2026

VerifiedLab: Harnessing Knowns for Unknowns

Across human history, knowledge has undergone several transitions, from orality to writing and then to digital archives. At each transition, humans established new conventions to preserve knowledge for the new era. Nowadays, as research agents are increasingly deployed for laboratory experiments, knowledge is crossing another boundary: from records written for humans to those for machines. In this work, we introduce VerifiedLab, a multi-agent harness framework for this human-to-machine transition of knowledge. VerifiedLab transforms research output from passive artifacts into active systems that accelerate downstream use, adoption and prediction of future trends. In VerifiedLab, a team of AI scientists with distinct roles reasons over records verified field by field: a principal investigator plans, a librarian computes the evidence directly from the records, specialists draft, and a gate and a critic check each claim against the measured reliability of its data before the harness decides whether to release or withhold it. We demonstrate the efficacy of VerifiedLab through extensive experiments on perovskite solar cells: VerifiedLab recovers known physical trends, anticipates devices reported a year later, and lets AI scientists inherit the literature together with a measure of how far it can be trusted. By scaling the inference-time verification compute, VerifiedLab introduces a new pathway for knowledge dissemination and machine harness for AI co-scientists.

cs.AI↗
arXiv2026

Beyond the Point Mass: Acceptance-Derived Weights and Distributional Losses for Speculative Decoding

In speculative decoding, a lightweight draft model proposes tokens that the target model verifies in parallel, speeding up generation without changing the target distribution. D-PACE (Wu et al., 2026) trains such drafters with a loss that weights each position by its contribution to the expected accepted length. Both its weights and its cross-entropy (CE) loss use only the draft's probability of the recorded target token, treating the target as a point mass. Under rejection sampling, however, a sampled draft token is accepted with probability equal to the overlap of the draft and target distributions, one minus their total variation (TV). We derive D-PAL (Dynamic Position-wise Acceptance Loss) from the exact expected accepted length, using this overlap as the acceptance signal. This yields overlap-based position weights with log acceptance (LA) as the per-position loss, and the objective reduces to D-PACE for a point-mass target. Since the weights are detached, any per-position loss can replace LA in practice. We show that forward KL divergence and Rényi divergence of order 1/2 match or exceed LA, and that Rényi-1/2 provably bounds the true acceptance rate from above and below. Replacing CE with Rényi-1/2 improves acceptance length under both D-PACE's weights and ours. On six benchmarks with a Qwen3-4B target, D-PAL raises mean acceptance length over D-PACE from 4.50 to 4.57 at T=0 and from 4.20 to 4.28 at T=1, and consistently achieves higher throughput at both temperatures.

cs.LG↗
arXiv2026

Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlow

MeanFlow predicts interval-average velocities, but conventional few-step sampling ties the interval queried from the model to the duration of the state update. We separate these two quantities at inference, fixing the model, update grid, and number of queries while varying the prediction horizon. Our central finding is that the horizon response depends on both query position and the states entering that query. Across seven independently trained CIFAR-10 checkpoints at classifier-free guidance (CFG) scale 2, a longer horizon worsens FID at early steps but improves it at the midpoint. To probe whether query time alone determines this response, we fix the midpoint query and current/subsequent guidance while changing only earlier CFG. In held-out factorial outcomes on five previously studied checkpoints, the mean midpoint horizon benefit increases from 0.109 to 1.308 FID, indicating sensitivity to the incoming-state distribution. A frozen four-query rule reduces mean CIFAR-10 FID by 2.023 without retraining or extra queries, including gains on five checkpoints trained after rule selection. A milder rule also improves mean FID by 1.041 on a stronger frozen grid, with fixed-rule FID gains on the evaluated public ImageNet-256 and AFHQ checkpoints. However, matched-budget calibration favors query-start shifting in historical CIFAR tests, and the tested Horizon allocation adds no FID benefit beyond Grid+Start on two public ImageNet models. Thus, prediction horizon is a distinct, position- and state-sensitive inference control, but not a universally preferred one.

cs.LG↗
arXiv2026

Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions

How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedrich Hayek's economic theory of decentralized coordination in markets, we study this question through an agent economy in which agents compete via auctions for the right to act, exchange payments, and accumulate wealth from environmental rewards. These simple local incentives induce decentralized credit assignment, driving global planning without explicit orchestration or communication protocols. The population evolves through economic selection: effective agents accumulate wealth and are mutated via exploitation, while ineffective ones go bankrupt and are replaced via exploration. Using modern Large Language Model (LLM) based agents, we show that, initialized with weak agents, the agent economy produces emergent multi-step reasoning strategies and outperforms stronger monolithic baselines across five agentic tasks, including mathematical reasoning, financial research, scientific research, accelerator design, and distributed-system optimization. Our results suggest a new path to multi-agent intelligence: rather than engineering coordination, we can design decentralized incentive structures under which it automatically emerges.

cs.CL↗
arXiv2026

SquidAgent: Parallelize Wisely, Coordinate Efficiently

LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency. In principle, parallelizing work across multiple agents should yield near-linear speedups. Yet existing parallel multi-agent systems often run slower than a single-agent baseline. We attribute this gap to two hidden costs that parallel execution incurs but a serial agent avoids. First, there is a re-exploration cost: redundant effort spent by parallel workers reconstructing context that the orchestrator already possesses, such as prior decisions, that would otherwise be inherited implicitly in a serial execution. Second, there is an alignment cost: the overhead required to reconcile inconsistencies across independently generated outputs. We thus derive a principled decision criterion: a layer should be parallelized only when its critical-path cost, plus re-exploration and alignment overheads, is lower than the corresponding serial cost. While this criterion is naturally expressed in wall-clock time, we observe that LLMs are poorly calibrated when asked to estimate task duration. To address this, we instead measure cost in predicted output tokens, which we empirically find LLMs can estimate substantially more reliably than wall-clock time. Building on this token-based criterion, we propose SquidAgent. It estimates all token budgets in a single planning step, forks each worker directly from the orchestrator's session to eliminate re-exploration cost, and replaces post-hoc reconciliation with a pre-generated shared convention block that converts alignment into a bounded upfront cost. A deterministic scheduler then applies the criterion layer by layer. Empirically, SquidAgent achieves a 2.2$\times$ mean throughput improvement and a 2.6$\times$ mean wall-time speedup over Claude Code, and a 2.0$\times$ throughput improvement over the strongest multi-agent baseline.

cs.AI↗
arXiv2026

Scalable Minimal-Change Learning for Controllable Image Editing

Image editing should change only the attributes specified by an instruction while preserving everything else, yet current methods often make unintended changes. We treat this minimal-change principle as an optimization objective for instruction-based editing. Latent L1 regularization is a poor proxy for output locality in modern nonlinear generators and often requires supervision unavailable at scale. We instead optimize edit outcomes with reinforcement learning. An agentic vision-language reward model audits each source image, instruction, and edited image for two failure types: unimplemented requested changes and unintended changes. A group-level rubric merges and verifies these issues to provide consistent rewards across candidate edits without per-instruction human annotations. On FLUX.1 Kontext-dev, ARRO raises average EditScore from 5.21 to 5.88 across MinEval, MagicBrush, AnyBench, and Emu-Edit. On 600 evaluation examples, it reduces off-target pixel change by 8.4% relative to the base editor. Reward and SFT controls, blinded human evaluations, and transfer to OmniGen2 provide complementary evidence. Code: https://github.com/Showwwwwwwww/ARRO

cs.CV↗
arXiv2026

Coupled-cluster molecular properties across the main group that extrapolate beyond training size

Coupled-cluster theory defines the accuracy standard for molecular electronic-structure properties but scales too steeply for routine application, whereas density-functional theory is affordable yet systematically biased. We resolve this trade-off with a single equivariant network, HARP (Hamiltonian Read-out for Properties), that predicts an effective one-electron Hamiltonian from one inexpensive B3LYP/def2-SVP calculation and derives a broad suite of properties from it (energy, optical gap, dipole, quadrupole, polarizability, Mulliken atomic charges, and Mayer bond orders) at coupled-cluster accuracy across nine main-group elements, including the under-served phosphorus, sulfur, and chlorine chemistries. The model is trained on a new in-house dataset of multi-property labels computed at the CCSD(T) level for all nine elements. On a held-out test set, it reduces the error of every property by a factor of 3.8 to 270 relative to semi-local, hybrid, and double-hybrid DFT (referenced to composite CCSD(T)/cc-pVTZ), while adding only ~0.1 s wall time per molecule, delivering coupled-cluster-quality predictions at the cost of a single DFT calculation. Critically, deriving every property from a predicted Hamiltonian rather than pooling per-atom features builds the correct size-scaling into the model architecture: on pi-conjugated oligothiophenes it matches finite-field CCSD polarizability to ~1% and the EOM-CCSD optical gap to ~3% at the largest sizes where those references remain affordable (44 and 37 atoms, where a single CCSD field point already costs ~500x the model's entire inference) and extrapolates the corrected trends to 58-atom chains, a regime where pooling-based architectures fail by construction. Accurate extrapolation is therefore set by the model's inductive bias rather than by the training data.

physics.chem-ph↗
arXiv2026

OrchSLM: Probing the Dynamics of Small Language Model Orchestration

Although large language models (LLMs) have demonstrated remarkable capabilities, their reliance on cloud-scale infrastructure poses fundamental challenges for deployment in agentic pipelines, including latency, privacy, connectivity, and substantial computational cost. Small language models (SLMs) offer a compelling alternative: recent studies suggest that many repetitive and narrowly scoped subtasks in agentic workloads may be better served by specialized SLMs than by monolithic LLMs. However, the limited capacity and context windows of SLMs can constrain long-horizon reasoning and interaction-heavy orchestration strategies such as iterative verification and debate. This motivates a complementary, non-interactive paradigm in which heterogeneous SLMs independently generate candidate solutions and a router orchestrates their cached samples without further model interaction. To further understand the mechanisms of such orchestration, we introduce OrchSLM, a routing framework that unifies existing non-interactive orchestration methods and exposes their underlying design choices as controllable parameters. Using OrchSLM as a systematic probe, we reveal how orchestration behavior emerges from diverse knobs, including the task structure, model-pool composition, and multi-agent consensus.

cs.AI↗
arXiv2026

Recovering Process Variables from Industrial Network Traffic via Search-Based Optimization

Process variables (PVs) provide the process evidence needed for process-aware security monitoring in industrial cyber-physical systems (CPSs). However, existing supervisory infrastructures expose only the subset of PV values recorded by historians, leaving many additional runtime PV values unobserved. To address this incomplete process visibility, we study the problem of recovering PV fields and their semantics directly from raw industrial network traffic through protocol reverse engineering (PRE). In this setting, existing PRE methods face two practical challenges: PV-carrying communication is mixed with heterogeneous runtime traffic, and PV-carrying payloads are often long and deployment-specific. Mixed runtime traffic obscures the PV-carrying communication paths, while long payloads create a vast segmentation space in which early segmentation errors can propagate and corrupt the recovery of later fields under sequential inference. In this paper, we formulate the recovery of PV fields from raw network traffic as a search-based optimization problem. Our key insight is that non-sequentially identifying correct segmentations in such a vast segmentation space can be cast as an optimization problem and addressed by searching for near-optimal solutions. We propose PVParser to approach this goal. PVParser first reduces the search space by identifying the PV-carrying payloads from network traffic via a periodic pattern detection mechanism. It then employs a modified Monte Carlo Tree Search to explore near-optimal segmentations, reducing error propagation from incorrect early boundary decisions. Experiments on three representative industrial CPS datasets demonstrate that PVParser achieves high accuracy and F1-score in PV-carrying payload localization and PV field inference, outperforming six state-of-the-art PRE approaches by a significant margin.

cs.CR↗
arXiv2026

AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning

Large language models (LLMs) achieve strong reasoning performance, which depends critically on inference-time decisions. Yet these decisions are commonly handled by static, one-size-fits-all policies, limiting adaptation to diverse tasks and reasoning stages. Recent adaptive methods partially address this limitation, but they primarily adapt either decoding stochasticity (how the model explores) or reasoning compute (how long the model reasons) in isolation, leaving their interaction within a single reasoning trajectory unmodeled. To address this challenge, we shift toward a within-trajectory joint control view, and instantiate it in AutoCRAT, a decoder-side controller for frozen backbones. Using only signals available during decoding, AutoCRAT jointly adjusts sampling stochasticity and reasoning budget during generation. AutoCRAT operates over a discrete action space and updates control decisions only at semantic boundaries, improving stability while remaining responsive to the evolving reasoning process. Comprehensive evaluation across 6 benchmarks demonstrates that AutoCRAT (I) uses 13.8-52.7% fewer inference tokens on average than recommended static configurations, (II) surpasses recommended static and adaptive baselines by 1.5-4.5% in relative accuracy, and (III) enjoys strong cross-backbone transferability.

cs.AI↗
arXiv2026

Towards Conditional Feature Alignment for Cross-Domain Counting

Object counting models often degrade under cross-domain deployment because density composition varies across domains and is itself task-relevant. Standard feature alignment methods tend to suppress such variation by encouraging global domain invariance, which can be harmful when source and target domains contain different proportions of background, sparse foreground, and dense foreground. We propose Conditional Feature Alignment (CFA), a cross-domain counting framework that aligns representations within label-induced conditions rather than across full marginal feature distributions. Given density annotations or pseudo-density predictions, CFA constructs foreground/background or density-level conditions and aligns only features belonging to matching conditions. We formalise this idea through a conditional divergence perspective, characterising an ideal conditionally aligned state with no within-condition discrepancy while preserving condition-marginal density shift. For unsupervised domain adaptation, CFA estimates source conditions from annotations and target conditions from detached pseudo-density maps, then performs condition-wise adversarial alignment with full-image consistency regularisation. For source-domain generalisation, we instantiate the same principle with MPCount by enforcing condition-wise memory-consistency between generated source-domain views. Experiments on crowd and cell counting benchmarks show competitive or improved performance across diverse UDA and DG settings. For example, on JHU-CROWD++ FH->SN, CFA-DG reduces MAE/RMSE from MPCount's 216.3/421.4 to 90.5/169.9, showing a marked improvement on this large weather- and density-induced shift. These results suggest that condition-wise alignment is a promising design principle for domain-adaptive counting.

cs.CV↗
arXiv2026

DRL-Based Secure Transmission for Rotatable Antenna-Enabled Low-Altitude ISAC Systems

The development of the low-altitude economy has driven innovation in intelligent antenna systems within ISAC systems. In this paper, we investigate a Rotatable Antenna (RA)-enabled low-altitude integrated sensing and communication (ISAC) system. In practical terms, the RA array can flexibly adjust the three-dimensional (3D) beam direction of each antenna to enhance array directional gain, thereby improving the communication security of legitimate mobile users against potential eavesdropping risks from the unmanned aerial vehicle (UAV). Our objective is to maximize the minimum secrecy rate (SR) by jointly optimizing transmit beamforming matrix, transmit and receive RAs' pointing matrices. To this end, an multi-agent proximal policy optimization with three improvement mechanisms (MAPPO-T) algorithm is proposed to cope with the issue of complex multi-agent collaborative decision-making problem. Simulation results show that the introduction of RAs can effectively improve SR performance compared to the traditional fixed orientation antenna (FOA)-based system. In addition, the proposed MAPPO-T algorithm validate the superiority compared to the standard MAPPO algorithm.

eess.SP↗
arXiv2026

MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting

In recent years, Transformers have become the de-facto architecture for long-term time series forecasting (LTSF), yet they face challenges associated with the self-attention mechanism, including quadratic complexity and permutation-invariant bias. This raises an important question: \emph{do we truly need self-attention to model long-range dependencies in LTSF?} To address this, we propose MambaTS, a linear-scan-based framework that models global dependencies across time and variables via structured dependency modeling. Since explicit variable dependency structures are often unknown, we introduce Variable-Aware Scan along Time (VAST), which learns inter-variable relationships during training and determines an optimal scan order via a shortest-path-based decoding strategy during inference. MambaTS employs the latest Mamba model as its backbone. We suggest that the causal convolution in the vanilla Mamba is unnecessary due to the presence of independent variables, leading to the development of the Temporal Mamba Block (TMB). To mitigate model overfitting, we further incorporate a dropout mechanism for selective parameters in TMB. Extensive experiments conducted on eight public datasets demonstrate that MambaTS achieves competitive or state-of-the-art performance on most datasets. Code is available at this repository: \href{https://github.com/XiudingCai/MambaTS-pytorch}{https://github.com/XiudingCai/MambaTS-pytorch}.

cs.LG↗
arXiv2026

Programmable Dynamic Phase Control of a Quasiperiodic Optical Lattice

The quantum dynamics of quasiperiodic systems display a rich variety of physical behaviors due to the combination of rotational symmetry that is mathematically forbidden in periodic systems, and long-range order despite the lack of translation symmetry. New experimental probes into these dynamics with a quantum simulator, consisting of ultracold atoms in an optical lattice potential, will yield new insights into the physics of quasiperiodic systems. This potential is imbued with the flexibility, tunability, and purity of the individual laser beams that constitute it, allowing for exquisite control over a rich system. Programmable dynamic control over the lattice beam phases opens up an even richer space of achievable systems via Floquet engineering. We thus describe an experimental scheme for creating a programmable, dynamic, two-dimensional (2D) quasiperiodic optical lattice with heavily suppressed phase noise. We observe suppression of phase noise for frequency components up to 5 kHz, and report phase noise suppression of over 70 dB over the DC-60 Hz frequency band. We further demonstrate a phase modulation bandwidth of 350 kHz. This scheme allows for full translational and phasonic control of the lattice, including changes to the rotational symmetry of the potential, at speeds exceeding the lattice recoil velocity, which paves a path towards direct observation and control of quantum dynamics in quasicrystals.

cond-mat.quant-gas↗
arXiv2026

HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks

Existing UAV vision-language navigation (VLN) benchmarks have enabled language-guided flight, but they largely focus on long, step-wise route descriptions with goal-centric evaluation, making them less diagnostic for real operations where brief, high-level commands must be grounded into safe multi-stage behaviors. We present HUGE-Bench, a benchmark for High-Level UAV Vision-Language-Action (HL-VLA) tasks that tests whether an agent can interpret concise language and execute complex, process-oriented trajectories with safety awareness. HUGE-Bench comprises 4 real-world digital twin scenes, 8 high-level tasks, and 2.56M meters of trajectories, and is built on an aligned 3D Gaussian Splatting (3DGS)-Mesh representation that combines photorealistic rendering with collision-capable geometry for scalable generation and collision-aware evaluation. We introduce process-oriented and collision-aware metrics to assess process fidelity, terminal accuracy, and safety. Experiments on representative state-of-the-art VLA models reveal significant gaps in high-level semantic completion and safe execution, highlighting HUGE-Bench as a diagnostic testbed for high-level UAV autonomy.

cs.CV↗
arXiv2026

Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling

Discrete diffusion models are widely used for learning and generating discrete distributions. As the generation process is inherently sequential, the acceleration of sampling is of significant importance. In this work, we parallelize the mainstream $τ$-leaping algorithm for absorbing discrete diffusion in a Continuous-Time Markov Chain (CTMC) framework. By leveraging the continuous-time stochastic integral form of the $τ$-leaping algorithm and the Picard iteration method, we achieve parallel-in-time sampling acceleration and provide a proof of exponential-factorial convergence for our algorithm. We improve the overall time complexity of $τ$-leaping under absorbing settings from ${\mathcal{O}}(d \log S)$ to ${\mathcal{O}}(\log (d\log S)\cdot \log d)$ with respect to NFE. Empirically, our method shows consistent acceleration across synthetic and real-data settings. The new sampler achieves at most $7$--$9\times$ runtime speedup for synthetic distribution, and maintains the same quality with $50\%$ fewer NFE and $1.45$--$1.86\times$ runtime speedups in image/text tasks on a single GPU. Our research expands the potential of discrete diffusion models for efficient parallel inference, with broader implications for applications such as molecular structure and language generation.

cs.LG↗
arXiv2026

ControlMap: Controllable High-Definition Map Generation for Traffic Scenario Simulation

Simulation is central to validating autonomous driving systems, yet current pipelines are limited by insufficient scenario diversity due to costly High Definition (HD) map creation. Scaling HD maps requires expensive data collection and manual processing. Moreover, existing generative models lack the fine-grained control necessary to target specific road topologies during generation. This paper presents a data-driven pipeline for controllable HD map generation using latent diffusion and ControlNet for spatial conditioning. To our knowledge, we are the first to inject spatial guidance signals into a diffusion model for HD map synthesis. Furthermore, our model supports adjustable conditioning strength through classifier-free guidance and city-level style transfer via city label conditioning. To complement existing metrics, we introduce two novel metrics to evaluate adherence to the control signal and similarity to ground-truth maps. Experiments demonstrate that our model generates realistic HD maps that faithfully follow input road topologies while accurately preserving city-specific details.

cs.RO↗