Searcharxiv⌕ Search

arXiv subjects

Yi Gao

Publications and source records attributed to Yi Gao.

At least 19 recordsLinked to original sources
arXiv2026

HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience

Extending Vision-Language-Action models (VLAs) to humanoid robots requires coordinated whole-body control and diverse demonstrations that are costly to collect in real-world scenarios. Although egocentric human demonstrations provide a complementary source of task experience, differences in visual embodiment and missing robot proprioception complicate transfer to humanoid policies. To address these challenges, we introduce HuGe, a family of Humanoid Generalist VLAs pre-trained on over 2,000 hours of egocentric human and robot data. Specifically, HuGe employs three existing representative VLA architectures to predict latent motion tokens for a pretrained whole-body controller, together with hand-control signals. Based on this, we introduce a three-stage training pipeline that combines egocentric pre-training, humanoid adaptation, and downstream fine-tuning. To facilitate transfer across embodiments, we construct pseudo-proprioceptive states through simulation playback during pre-training and modify arm appearance in egocentric observations through re-rendering during downstream fine-tuning. With this pipeline, HuGe achieves the state-of-the-art on simulation benchmark HumanoidArena. Furthermore, real-world experiments on the Unitree G1 indicate that augmenting robot demonstrations with visually adapted egocentric demonstrations significantly increases success on a pick-and-drop task.

cs.RO↗
arXiv2026

Beyond Explicit Intent: Discovering and Shaping Artistic Intent through Human-AI Co-Creation

Generative AI is becoming an important medium for artistic creation, yet existing interactions often assume that creators can specify intentions in advance and accurately communicate them through text prompts. Artistic intentions, however, may be vague, latent, or recognizable only after seeing concrete visual possibilities. We propose a human-AI co-creation paradigm beyond explicit intent expression. By expanding model exploration, we expose artists to diverse visual possibilities, allowing them to identify previously unarticulated preferences through observation, comparison, and selection. We then integrate artists' curatorial judgments into reinforcement learning, assigning different learning strengths based on preferences over generation trajectories, so recognized directions are more strongly reinforced and the model gradually adapts to individual aesthetics. This creates a continuous "explore-identify-shape-re-explore" loop in which artistic intent is progressively discovered, externalized, and shaped. Through three user studies, we examine latent-preference discovery, personalized preference alignment, and the externalization of vague, difficult-to-express creative intentions.

cs.AI↗
arXiv2026

Extreme points of the unit balls and isometries of noncommutative quasi-Banach Marcinkiewicz spaces

We characterize extreme points of the (positive) unit balls of Marcinkiewicz spaces with respect to their natural quasi-norms. Having these results at hand, we show that every positive surjective isometry on a noncommutative Marcinkiewicz space is of elementary form. In particular, a linear mapping on a noncommutative Marcinkiewicz space over an atomic von Neumann algebra with all atoms having the same trace is a positive surjective isometry if and only if it is the restriction of a Jordan $*$-isomorphism which preserves the singular value functions. We also study (not necessarily positive) surjective isometries on weak $L_p$-spaces affiliated a $σ$-finite non-atomic von Neumann algebra for $1 0$, as well as one-parameter groups of isometries on the latter two.

math.FA↗
arXiv2026

Composition without a Host: Carrying the Spatiotemporal-Composability Guarantee of Plugin-Based Agents across Processes

Plugin-based agents assemble capabilities at runtime, and the spatiotemporal-composability calculus proves a reversibility guarantee for this assembly. However, the guarantee is carried by a single process, which confines all components, sessions, and recovery records to one failure domain, where a fault spreads past the plugin boundary, and process death interrupts every session the process hosts. Resting only on the hypotheses the calculus already states and the stateless interface of the model call, this paper relaxes the single-process restriction of the calculus to an arbitrary assignment of components and records to processes, gives four sufficient conditions, and proves with Theorem 1, derived from the four lemmas, that the reversibility guarantee holds across processes when these conditions are met. Based on Theorem 1, this paper constructs Logos, a cross-process plugin-based agent in the peer-process and name-routed form of ROS, where a plugin is a process, the router holds only a rebuildable routing table, and the session state needed for recovery lives in an append-only transcript owned by no process. Under one fault on two hundred benchmark tasks across three configurations, the single-process reference lost every session and scored 1.5 percent on the official validator, the MCP configuration kept its sessions while spending 1099 calls on a dead endpoint, and Logos kept every session alive, wasted zero calls, and succeeded on 120 tasks against 102 for both configurations combined. At the mechanism level, eighty sessions terminated at four points of the tool-call cycle all resumed with no repeated action, 3,500 concurrent calls paired with zero violations, and one bus hop cost 1 in 823 of the model's first token. The results show that the reversibility guarantee holds across processes and that assembly itself can leave the host process.

cs.AI↗
arXiv2026

AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement

Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives. Intuitively, more researcher agents can explore more hypotheses, but early evaluation scores might misrepresent their promise, shared findings could lose their applicability conditions, and useful procedures could remain confined to completed investigations. In this paper, we present AReaL-RSI, a framework for organizing a persistent research team of agents without updating backbone LLM weights. We formulate the scaling problem in terms of evaluated outcomes and whole-system resource expenditure. Concretely, a leader agent selects task-appropriate research orientations and guides ongoing investigations; conditional memory sharing distinguishes unresolved problems from supported findings and enables recipient adaptation. During recursive evolution, after each campaign, evidence-based review revises researcher orientation, knowledge, and skills for later campaigns. Experiments compare AReaL-RSI with Codex-Goal on downstream harness optimization, GPU kernel optimization, and AI research tasks using two backbones. Under the reported resource allocations, AReaL-RSI improves Terminal Bench performance by 2.2 percentage points for each backbone and increases mean KernelBench speedup by 32.2-36.8%; further scalability comparisons favor the design of AReaL-RSI over native scaling: combining experience sharing with specialized researcher roles yields 1.9-27.5% lower kernel latency than independent exploration and 1.3-33.9% lower latency than sharing alone across all seven comparable task-backbone pairs.

cs.AI↗
arXiv2026

Event-Aligned Visual Action Reasoning for World Action Models

World-Action Models (WAMs) utilize future visual prediction as an intermediate reasoning process to guide action generation. However, existing WAMs typically structure visual imagination according to predefined temporal intervals, without explicitly accounting for the different roles of task-critical interactions and connecting transitions. We argue that effective visual foresight should align directly with task-relevant interactions and their corresponding reasoning demands. To this end, we introduce an event-aligned visual action reasoning framework that organizes visual-action prediction around interaction events. Through event-aligned visual-action supervision, WAM learns to generate event-aligned visual context in each imagined rollout, placing greater emphasis on critical state changes that inform action generation. This shapes the visual reasoning granularity according to the underlying interaction dynamics, with detailed reasoning around task-critical events and coarser progression through connecting transitions. Furthermore, we introduce an execution validity head that identifies the valid portion of each predicted action sequence, avoiding redundant actions during chunked inference. Experiments demonstrate a 10.26 percentage point improvement in DOMINO success rate over baseline and competitive performance on RoboTwin 2.0. It also transfers from DOMINO Level 1 to Levels 2 and 3 without target-level adaptation.

cs.CV↗
arXiv2026

Autocata: Reaction-network-guided autonomous catalyst screening via capability-centric AI

Artificial intelligence (AI) has expanded the accessible space for catalyst discovery, yet executing complex screening campaigns still requires constant human intervention to bridge high-level reaction objectives with underlying computational pipelines. Here, we present Autocata, a knowledge-embedded autonomous agent that scales catalytic expertise by encoding multistep reaction pathways into reusable, language-invocable capabilities. Powered by a Transformer pretrained on two million catalyst-adsorbate structures, the system incorporates a capability registry of 79 adsorbate-specialized generative models spanning complex reaction networks across carbon, nitrogen, oxygen, and hydrogen intermediates. Given a high-level natural-language prompt, Autocata deconstructs reaction networks, queries and configures matching generative models, generates candidate surface configurations, enforces physical and geometric validity filtering, and coordinates machine-learning potentials evaluations to rank promising materials. Crucially, the agent adaptively reconfigures workflows when encountering capability boundaries or task bottlenecks. We demonstrate these capabilities across CH4 activation, nitrogen reduction reaction (N2RR), and CO2-to-methanol pathways. By shifting from static toolkits to an adaptive, language-driven computational infrastructure, Autocata lowers the barrier for expert-level catalyst discovery and offers a scalable paradigm for self-driving catalytic research.

physics.chem-ph↗
arXiv2026

Q-WAM: 4-Bit Quantization of World Action Models with Action-Subspace Protection

World Action Models (WAMs) jointly generate video and robot actions through iterative diffusion and perform strongly in robotic manipulation. However, their prohibitive compute and memory costs pose substantial deployment challenges. Post-training quantization (PTQ) can reduce these costs, but existing PTQ methods such as smoothing and rotation are insufficient to maintain the precision of action generation. To overcome this limitation, we propose Q-WAM, a new 4-bit weight-activation quantization for WAMs that preserves the actions the model generates. Specifically, we introduce the \textit{Action Observability Gramian (AOG)}, which measures how much rounding errors in each weighted combination of a layer's input channels change the final action through all denoising steps. We also develop Action-Subspace Protection (ASP), which keeps the few most action-sensitive channel combinations in a tiny 16-bit low-rank branch and quantizes the complementary weights and activations to 4 bits, both as dense matrix multiplications that run efficiently on GPUs. Finally, to preserve action quality with minimal overhead, we identify the experts that matter most for the generated action by aggregating the AOG-derived action mass across the layers of each expert and apply ASP only to those experts. We evaluate Q-WAM on three WAMs, both in simulation and in real-world deployment. On the RoboTwin 2.0 benchmark, it reaches 89.6--93.0\% average success rate, within 1.1 percentage points of the 16-bit models, while reducing the memory of the quantized blocks by 3.1--3.4$\times$. Our method outperforms the strongest baseline, SVDQuant, by 2.5--8.7 percentage points. On a Unitree G1 humanoid and a bimanual UR3 robot, it improves success over SVDQuant by 12.8-17.6 percentage points.

cs.RO↗
arXiv2026

A Cycle-Consistency Constrained Framework for Dynamic Solution Space Reduction in Noninjective Regression

To address the challenges posed by the heavy reliance of multi-output models on preset probability distributions and embedded prior knowledge in non-injective regression tasks, this paper proposes a cycle consistency-based data-driven training framework. The method jointly optimizes a forward model Φ: X to Y and a backward model Ψ: Y to X, where the cycle consistency loss is defined as L _cycleb equal L(Y reduce Φ(Ψ(Y))) (and vice versa). By minimizing this loss, the framework establishes a closed-loop mechanism integrating generation and validation phases, eliminating the need for manual rule design or prior distribution assumptions. Experiments on normalized synthetic and simulated datasets demonstrate that the proposed method achieves a cycle reconstruction error below 0.003, achieving an improvement of approximately 30% in evaluation metrics compared to baseline models without cycle consistency. Furthermore, the framework supports unsupervised learning and significantly reduces reliance on manual intervention, demonstrating potential advantages in non-injective regression tasks.

cs.LG↗
arXiv2026

HMGCLIP: Heterogeneous Multi-Granularity Contrastive Learning for E-commerce Representation Learning

Although recent Multimodal Large Language Models (MLLMs) have advanced general product understanding, they implicitly encode product information into global embeddings, thereby limiting their ability to capture fine-grained attributes. This limitation hinders performance in tasks requiring precise attribute discrimination, such as distinguishing subtle material differences among visually similar products. To address this challenge, we propose HMGCLIP, a unified multimodal embedding framework. By constructing a heterogeneous hypergraph, we leverage hypergraph topology to mine structure-aware hard negatives and align multi-granular semantics at both relation and hyperedge levels. This design enables a dual-granularity inference mechanism that dynamically fuses attribute evidence for both fine-grained and coarse-grained downstream tasks. Furthermore, we release a comprehensive fine-grained e-commerce dataset to facilitate future benchmarking. Extensive experiments on this new dataset and the public MAVE benchmark show that HMGCLIP outperforms strong multimodal encoders, MLLMs, and e-commerce baselines, validating the superiority of HMGCLIP.

cs.AI↗
arXiv2026

Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT

Translating C code into safe, idiomatic Rust is a longstanding software-engineering goal because it can eliminate entire classes of memory-safety vulnerabilities while preserving the functional behavior of legacy systems. Large language models (LLMs) have shown promise for this task but typically underperform when applied off-the-shelf, since general-purpose pretraining rarely emphasizes idiomatic Rust generation, cross-language semantic equivalence, or the ability to reason about and repair compiler/runtime feedback. In this report we describe a three-stage fine-tuning curriculum applied to Qwen3-27B that is designed to progressively specialize the model for the C-to-Rust (C2Rust) translation task: (1) continued pretraining on Rust-centric corpora to strengthen the model's prior over idiomatic Rust syntax and standard-library usage; (2) supervised fine-tuning (SFT) on the microsoft/Verus_Training_Data dataset to instill debugging and self-repair behavior over Rust code; and (3) task-specific SFT on paired C/Rust solutions derived from LeetCode problems to teach direct semantic translation. We evaluate the resulting model using the agentic, static-analysis-guided verification framework of SACTOR, which performs structure-aware, two-phase (unidiomatic to idiomatic) translation with foreign-function-interface (FFI)-based end-to-end (E2E) testing. We report success rate, idiomaticity (Clippy lint counts, unsafe-code fraction), and failure-mode analyses, and compare our fine-tuned model against baseline Qwen3-27B and other LLMs evaluated under the same framework.

cs.SE↗
arXiv2026

Schedule-Informed Temporal Fusion Forecasting of Hourly Airport Security-Checkpoint Throughput

Checkpoint staffing requires accurate forecasts of when screening demand will occur, yet flight schedules record departure times rather than passenger arrival times at security checkpoints. This study develops a framework that converts known flight schedules into temporally aligned signals for forecasting hourly checkpoint throughput. Using 2023-2024 Transportation Security Administration throughput data and Cirium Diio flight schedules for Hartsfield-Jackson Atlanta International Airport, domestic and international seat capacity was distributed across pre-departure hours using truncated Poisson kernels. A Temporal Fusion Transformer then combined these schedule-derived arrival-intensity signals with historical throughput, scheduled activity, and temporal variables. Models were trained chronologically, with July-December 2024 reserved for testing, and evaluated against recurrent neural network and long short-term memory models across five random seeds. For direct six-hour forecasts, the proposed model achieved a weighted mean absolute percentage error of 9.33%, compared with 12.16% for the recurrent neural network and 11.37% for long short-term memory, while also producing the lowest errors during peak periods. With six-hour recursive updates, errors remained between 10.60% and 11.04% across 24-96 hour horizons, although longer horizons contained fewer valid forecast origins. By transforming scheduled departures into interpretable pre-departure screening-load signals without requiring passenger-flight matching, the framework supports advance staffing, lane-opening, and multiday checkpoint planning. Because observed throughput reflects realized processing rather than unconstrained arrivals, the forecasts should be interpreted together with local staffing, capacity, queue, and wait-time information.

cs.LG↗
arXiv2026

AReaL-DTE: Sparse Policy-Weight Transfer for Online Agentic Reinforcement Learning

Online agentic reinforcement learning implemented with micro-services separates policy training from rollout generation, improving scalability and modularity while potentially making frequent policy-weight synchronization a critical systems overhead. Shared storage naturally connects these services across clusters, but vanilla dense policy weight synchronization could incur model-scale construction, transfer, and application costs. Sparse synchronization reduces transferred data, yet checkpoint-oriented approaches can still retain a previous model and materialize complete intermediates to bridge heterogeneous training and inference layouts. We present AReaL-DTE, a snapshot-free Delta Transfer Engine that translates inference-visible weight sparsity into end-to-end system efficiency. Across our evaluated workloads, fewer than 2% of BF16 weight elements change between consecutive policy versions. AReaL-DTE reconstructs overwritten weights on demand by inverting AdamW updates, streams reconstructed and current parameters through converter-aligned BF16 change detection, and remaps changed elements directly into receiver-local coordinates. AReaL-DTE supports manifest-committed sparse transfer through shared storage across clusters and a deadlock-safe two-round protocol within a cluster, followed by direct application to inference shards. We evaluate AReaL-DTE on Qwen3-8B and Qwen3-30B-A3B across four online RL workloads. AReaL-DTE achieves speedups of up to 19.9x over ByteCheckpoint and 3.2x over PULSE across clusters, and up to 7.6x and 7.4x, respectively, within a cluster. In the same-cluster Qwen3-30B-A3B experiments, it reduces peak GPU memory by approximately 41% and peak CPU memory by at least 87%.

cs.DC↗
arXiv2026

Reaction-Network-Level Discovery of Ammonia Synthesis Catalysts via Ten-Million-Scale Generative Exploration

Catalyst discovery for ammonia synthesis is inherently a reaction-network challenge because catalytic performance is governed not by a single adsorbed intermediate, but by a surface's orchestrated compatibility with multiple distinct intermediates across competing dissociative and associative pathways. However, navigating ultra-large chemical spaces under such multi-intermediate constraints remains a formidable bottleneck for conventional screening workflows. Here, we report a reaction-network-level catalyst discovery framework driven by ten-million-scale generative exploration. By coupling adsorbate-specific generative Transformers with high-throughput machine learning potentials, we systematically map the structure-property landscapes of four critical intermediates (N*, NH*, NNH*, and HNNH*). Scale-dependent overlap analysis shows that the full four-intermediate compatibility space remains strongly under-sampled at conventional 105-106 generative scales, emerging exclusively under ten-million-scale exploration. By generating approximately 15 million configurations per adsorbate, followed by structural compression and machine-learning-potential predictions, we identified 279 highly potential target materials. This sparse compatibility space successfully recovers traditional Fe- and Ru-based motifs while uncovering previously unexplored catalyst families. Representative DFT calculations validate pathway-dependent mechanisms: Fe-V emerges as a dissociative-pathway lead by significantly lowering the initial N2 dissociation barrier, whereas Al-Pd-Zr efficiently stabilizes associative intermediates as an associative-pathway lead. These findings establish multi-intermediate reaction-network compatibility as a robust criterion for discovering advanced catalysts from multi-million generative chemical spaces.

physics.chem-ph↗
arXiv2026

GUIMigrator: Semantics-Preserving Transpilation from Android XML to Compose and SwiftUI

Constructing user interfaces (UIs) is one of the most resource-intensive tasks in mobile development, often consuming more than half of overall effort. Although declarative frameworks such as Jetpack Compose (Android) and SwiftUI (iOS) have become mainstream, the majority of existing Android apps still rely on legacy XML-based layouts. Migrating these UIs to declarative paradigms is essential for maintainability and cross-platform reuse, but manual migration is costly, error-prone, and difficult to scale. We present GUIMigrator, a semantics-preserving framework that automates the migration of Android XML-based UIs to Jetpack Compose and SwiftUI. We design the Semantic UI Transpiler (SUT), which abstracts layout structures and resource semantics from legacy XML and systematically re-expresses them using the component abstractions and idioms of modern declarative frameworks. This design ensures that migrated UIs preserve both visual fidelity and functional equivalence, while generating idiomatic, compilable code that maintains cross-platform consistency with minimal manual intervention. By separating semantic interpretation from platform-specific realization, GUIMigrator provides a deterministic yet extensible basis for cross-platform modernization, avoiding the unpredictability of purely generative approaches. We evaluate GUIMigrator on 31 open-source applications across ten domains. Results show that GUIMigrator achieves high migration completeness and strong visual similarity (81.9% SSIM on Jetpack Compose and 78.2% on SwiftUI on average), while maintaining substantially higher project-wide semantic coherence (PSC) than modern LLM baselines. In addition, GUIMigrator reduces manual development effort by over 90%.

cs.SE↗
arXiv2026

IntentTester: Intent-Driven Multi-agent Framework for Cross-Library Test Migration

Unit tests capture both functional checks and domain-specific knowledge, but this knowledge remains locked within individual projects and is rarely reused across libraries with overlapping functionality. Existing migration techniques based on structural code mappings (e.g., API signatures) often break down under divergent designs or cross-language settings, resulting in non-executable migrated tests. In this paper, we present IntentTester, a multi-agent framework for intent-driven test reuse. Instead of translating raw code, IntentTester abstracts tests into a language-agnostic Test Description Language (TDL), aligns them with semantically related entities and dependencies in a repository graph, and synthesizes executable tests through LLM-guided reasoning and iterative validation. This design enables cross-library and cross-language migration without manual intervention, producing migrated tests that existing structure-mapping approaches cannot achieve. We evaluate IntentTester on nine open-source projects across three domains (JSON, HTML, and Time) and two languages (Java and Python). IntentTester generates 2,776 syntactically correct tests with 85\% correctness; in comparison, the two baselines achieve 51\% and 43\%. Among them, 2,410 tests executed successfully, yielding a 74\% effectiveness rate. Beyond higher success rates, IntentTester also surfaced previously unknown defects including stack overflows, null dereferences, and parsing inconsistencies, several of which have been acknowledged or patched by maintainers. Our results show that intent-driven migration shifts the focus from code mappings to semantic alignment, allowing practical cross-library and cross-language test reuse while improving test quality and exposing implementation flaws.

cs.SE↗
arXiv2026

ChatMOSP: A Chemistry-Grounded Mobile Agent for Working-State Catalyst Simulations

Catalytic nanoparticles restructure dynamically under reaction conditions, so their working morphology and activity are governed by temperature, pressure, and gas composition. However, converting experimentally specified environments into physically meaningful morphology-performance simulations remains difficult because the translation of reaction conditions into model-specific energetic, kinetic, and execution parameters requires the specialized knowledge in computational catalysis. Here we report ChatMOSP, a chemistry-grounded mobile scientific agent that translates natural-language and voice-expressed catalytic requests into parameter-validated simulations using the Multi-scale Operando Simulation Package. ChatMOSP maps catalyst identity, temperature, pressure, gas composition, and target observables onto multiscale structure reconstruction and kinetic Monte Carlo tasks, retrieves database parameters or constructs missing inputs from an online literature-retrieval workflow, and executes validated MOSP workflows. Using CO oxidation on Pd nanoparticles as an example, we verify the ChatMOSP simulations capture the temperature-induced transition from faceted to rounded morphologies observed by in-situ TEM experiments either by built-in database or from web-retrieved literature information when the parameters are absent. Moreover, we demonstrate the capability of ChatMOSP to perform end-to-end study at mobile devices to simulate a pressure-coverage-morphology-activity feedback cycle for Pt CO oxidation to interpret the oscillatory CO conversion. These results establish ChatMOSP as a physically constrained mobile agent for accessible and interpretable catalyst working-state simulations.

cond-mat.mtrl-sci↗
arXiv2026

AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction

Product attribute extraction in e-commerce is bottlenecked by ontologies that are inconsistent, incomplete, and costly to maintain. We present AutoPKG, a multi-agent Large Language Model (LLM) framework that automatically constructs a Product-attribute Knowledge Graph (PKG) from multimodal product content. AutoPKG induces product types and type-specific attribute keys on demand, extracts attribute values from text and images, and consolidates updates through a centralized decision agent that maintains a globally consistent canonical graph. We also propose an evaluation protocol for dynamic PKGs that measures type and key validity, consolidation quality, and edge-level accuracy for value assertions after canonicalization. On a large real-world marketplace catalog dataset from Lazada (Alibaba), AutoPKG achieves up to 0.953 Weighted Knowledge Efficiency (WKE) for product types, 0.724 WKE for attribute keys, and 0.531 edge-level F1 for multimodal value extraction. Across three public benchmarks, our method improves edge-level exact-match F1 by 0.152 and yields a precision gain of 0.208 on the attribute extraction application. Online A/B tests show that AutoPKG-derived attributes increase Gross Merchandise Value (GMV) in Badge by 3.81 percent, in Search by 5.32 percent, and in Recommendation by 7.89 percent, supporting the practical value of AutoPKG in production.

cs.AI↗