Searcharxiv⌕ Search

arXiv subjects

Ming Liu

Publications and source records attributed to Ming Liu.

At least 19 recordsLinked to original sources
arXiv2026

DualEvolve: Dual-Level Self-Evolution of Mechanism and Orchestration for Recommendation

Recommender systems are widely used in e-commerce and content platforms, where improvement requires repeated model design, training optimization, and experimental validation. Large language model (LLM) agents increasingly automate this development cycle. Sustained autonomous improvement requires agents to improve both recommendation models and their development workflows. However, task-performance-driven approaches select updates mainly by candidates' final scores, without a separate optimization signal for experimentation quality. We therefore present DualEvolve, a dual-level framework that co-evolves recommendation mechanisms and agent orchestration toward recursive self-improvement. Inner evolution revises model and training code using task feedback to improve recommendation performance. Outer evolution scores the inner-loop experimental process, updates harness and skill rules using these scores and execution traces, and adjusts orchestration choices based on next-round scores to improve the quality of subsequent experiments. Experiments on MovieLens-1M and three Amazon Reviews 2023 subsets cover four recommendation methods and 16 settings. DualEvolve achieves higher test means than Base, OpenEvolve, and DeepEvolve in all 64 setting-metric comparisons, with macro-averaged relative gains over DeepEvolve of 7.6% (HR@5) and 9.0% (NDCG@5).

cs.IR↗
arXiv2026

Goal-Driven Autonomous Optical Experimentation via a Self-Recursive Hardware-Software Harness

We propose goal-driven self-recursive optical research in which agents use physical evidence to revise the hardware, software, models, and protocols used to pursue a scientific goal. The framework can be instantiated with different stimulus systems and measurement devices. We formalize its updates and derive a relation between physical attainability, command access, and model approximation error. We demonstrate the concept in an optical see-through color-matching case study using an iPad, RayNeo X3 glasses, and a TOP 300 probe coupled to a CAS140D spectroradiometer, both from Instrument Systems. A revised glasses application adds USB-controlled RGB holds and frame acknowledgements, keeping model-generated colors displayed during spectral acquisition. The interface passes 12 live control checks. Spectral feedback reduces one target color difference from 19.756 to 1.211 ΔE_76^*; all five targets improve in a separate comparison. These measurements demonstrate the concept in one configuration. The resulting software and protocols remain available for subsequent investigations.

cs.AI↗
arXiv2026

RecRSI: Mechanism-Guided Discovery of Recommendation Algorithms

Improving recommendation algorithms for the Web requires coordinating interacting design choices and learning from experiments. We present RecRSI, an LLM-based research framework that uses mechanism hypotheses to organize algorithm discovery. Each hypothesis links a proposed mechanism change to a reference design, a rationale, and an expected observation. MechSpace derives implementable primitives and composition rules from the task source; Research Line uses this space and prior evidence to develop and test hypotheses; Mechanism Feedback carries outcomes and their design context into subsequent research. This organization makes each experiment inform which mechanisms to develop, revise, or combine next. Across four initial recommenders and four datasets, RecRSI yields average relative improvements of 8.48% in NDCG@5 and 6.88% in HR@5 over the initial algorithms, and 2.60% and 2.20%, respectively, over the strongest competing result for each setting and metric. Component and process studies link these gains to coordinated mechanism choices and evidence-guided follow-up. Our code is publicly available at https://github.com/DynamisG210/RecRSI.

cs.IR↗
arXiv2026

NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving

Recent perception-free end-to-end (E2E) autonomous driving methods bypass explicit perception outputs by compressing dense image patch tokens into compact scene tokens for downstream trajectory generation and scoring. While these scene tokens form a compact visual bottleneck for the planner, they receive supervision solely from the planning objective, providing limited constraints on the encoded visual information. To address this limitation, we introduce Neural Token Reconstruction (NTR), a representation learning framework to directly constrain the compact scene-token bottleneck in perception-free driving. NTR introduces a self-distillation masked latent reconstruction objective that reconstructs masked patch-level latent features using only compact scene tokens as reconstruction memory. This forces reconstruction gradients to pass exclusively through the scene-token bottleneck, encouraging scene tokens to preserve richer and less redundant visual representations for planning. We further introduce semantic priors derived from foundation-model annotations as a weak semantic interface biasing reconstruction targets toward driving-related structures without introducing explicit perception heads. All auxiliary reconstruction components are removed at inference time, leaving the deployed planner unchanged. NTR achieves state-of-the-art performance on three public autonomous driving benchmarks, including 8.0461 RFS on Waymo E2E and 94.1 PDMS / 90.9 EPDMS on NavSim1&2. The learned scene tokens exhibit lower pairwise redundancy and higher effective rank, indicating that effective bottleneck supervision improves both compact visual representation learning and planning performance.

cs.CV↗
arXiv2026

CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents

A memory can be outdated for present-day reasoning yet indispensable for reconstructing the past. Relevance-based retrieval overlooks this tension: semantic relevance, evidence-grounded validity, and query-specific eligibility are distinct. We propose CALM, a conflict-aware lifecycle memory governance framework that decouples persistent memory preservation from query-time admission. CALM converts heterogeneous records into evidence-grounded memory cells, updates validity and lifecycle states using support, conflict, and dependency signals, and admits query-appropriate evidence through training-free or learned gating informed by temporal applicability. Across LongMemEval-S and LoCoMo with Qwen and GPT backbones, CALM outperforms state-of-the-art baselines, achieving the best overall accuracy. Compared with simple filtering and reranking, query-conditioned admission further improves evidence selection. Conflict-blocking and robustness analyses show CALM suppresses erroneous retrieved memories while retaining useful evidence. Historical-reconstruction experiments demonstrate that preserving superseded records supports accurate earlier-state reasoning without compromising current-state answers.

cs.AI↗
arXiv2026

Uncovering Shortcut Amplification in Video RLVR through the Lens of Perceptual Uncertainty Collapse

Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for enhancing the video reasoning capability of Large Multimodal Models (LMMs). Despite its empirical effectiveness, we show that outcome-level optimization can introduce an undesirable shortcut amplification effect, whereby models increasingly favor text-prior answers even when they are not supported by the visual evidence. To characterize this behavior, we investigate the training dynamics of video RLVR through the lens of perceptual uncertainty, analyzing how predictive uncertainty evolves under video-conditioned and text-only contexts. Our analysis identifies a perceptual uncertainty collapse phenomenon, in which RL training continuously sharpens the model's answer distribution while the uncertainty reduction attributable to visual evidence progressively diminishes. A further gradient-direction analysis reveals that such confidence enhancement becomes increasingly less aligned with visually grounded uncertainty reduction and is instead dominated by text-prior compression. Motivated by these findings, we propose Bifocal Self-distillation Policy Optimization (BSPO), a self-distillation framework that regulates policy updates with two complementary distributional signals. Specifically, BSPO derives empirical reasoning principles from intra-group correct and incorrect rollouts to identify reasoning-sensitive tokens, and introduces shortcut-aware visual perturbation to penalize predictions that remain invariant when task-relevant visual evidence is weakened. By adaptively reweighting the original RL advantage, BSPO preserves the task-solving benefits of RLVR while promoting updates that are both reasoning-sensitive and visually grounded. Extensive experiments validate the effectiveness of BSPO in improving video reasoning performance and strengthening visual faithfulness.

cs.CV↗
arXiv2026

FICGen: Frequency-Inspired Contextual Disentanglement for Layout-driven Degraded Image Generation

Layout-to-image (L2I) generation has exhibited promising results in natural domains, but suffers from limited generative fidelity and weak alignment with user-provided layouts when applied to degraded scenes (i.e., low-light, underwater). We primarily attribute these limitations to the "contextual illusion dilemma" in degraded conditions, where foreground instances are overwhelmed by context-dominant frequency distributions. Motivated by this, our paper proposes a new Frequency-Inspired Contextual Disentanglement Generative (FICGen) paradigm, which seeks to transfer frequency knowledge of degraded images into the latent diffusion space, thereby facilitating the rendering of degraded instances and their surroundings via contextual frequency-aware guidance. To be specific, FICGen consists of two major steps. Firstly, we introduce a learnable dual-query mechanism, each paired with a dedicated frequency resampler, to extract contextual frequency prototypes from pre-collected degraded exemplars in the training set. Secondly, a visual-frequency enhanced attention is employed to inject frequency prototypes into the degraded generation process. To alleviate the contextual illusion and attribute leakage, an instance coherence map is developed to regulate latent-space disentanglement between individual instances and their surroundings, coupled with an adaptive spatial-frequency aggregation module to reconstruct spatial-frequency mixed degraded representations. Extensive experiments on 5 benchmarks involving a variety of degraded scenarios-from severe low-light to mild blur-demonstrate that FICGen consistently surpasses existing L2I methods in terms of generative fidelity, alignment and downstream auxiliary trainability.

cs.CV↗
arXiv2026

Alignment-Free Optical Combining with Scalar-Message Expectation Propagation Detection for Distributed Multi-Aperture Coherent Reception

We propose an alignment-free distributed multi-aperture optical receiver with a single coherent front end, in which the differential delays between apertures are large. The branch signals are optically combined without inter-branch delay or phase alignment. Large differential delays produce separated tap clusters, forming a sparse ISI channel with long memory. Scalar-message expectation propagation exploits this sparsity to recover the transmitted symbols. Simulations show lower BER than equal-area single-aperture reception and no clear BER degradation over the tested delay spans. As the maximum differential delay increases from 100.5 to 200.5 symbol periods, the channel span nearly doubles, while the factor-graph edge count increases by only about 1.5\%. The trade-off is higher BER than ideal coherent combining schemes in exchange for fewer coherent front ends than digital combining and no inter-branch delay or phase alignment before optical combining.

physics.optics↗
arXiv2026

LiBRA: Logit Fingerprints for Byzantine-Robust Client Selection in Federated Learning

Byzantine-robust aggregation shields federated learning from malicious updates, but the rules that filter out suspect updates do so by comparing clients' parameter vectors. That comparison requires access to every client's update, which secure aggregation exists to withhold, costs $O(n^2 d)$ in the parameter dimension $d$, and is defined only between clients that share an architecture. We propose LiBRA, which compares clients on what their models compute rather than on the parameters that compute them, using a fingerprint of $C^2$ values for $C$ classes, the class-conditional logit response of each client's model to pseudo-patterns optimised against it. We instantiate LiBRA as variants of Krum, Multi-Krum and Bulyan that change only what the dissimilarity score is computed on. On Fashion-MNIST and CIFAR-10 with three architectures and four backdoor and label-manipulation attacks under i.i.d. partitions, each variant holds every attack its parent holds, and on identical client updates under a backdoor attack the fingerprint ranks malicious clients within 0.006 AUC of the full parameter vector. The variants thus match the robustness of the rules they extend, while their trust decision reads no client parameter, compares up to 49,090 times fewer values, and can by construction compare clients whose architectures differ, at the cost of one pattern optimisation per client per round.

cs.LG↗
arXiv2026

Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification

Knowledge Graphs (KGs) provide a critical foundation for many AI systems, yet their automated construction inevitably introduces noisy triples that undermine data trustworthiness. Reliable KG auditing requires jointly examining internal structural constraints and open-world evidence, whereas existing methods often rely on a single evidence source or static, one-shot inference, limiting adaptive evidence acquisition and auditability. We propose SHARP (Schema-Hybrid Agent for Reliable Prediction), a training-free agent that reformulates triple verification as a dynamic process of strategic planning, active investigation, and evidential reasoning. SHARP uses retrieved historical verification trajectories and entity--relation schema information to construct a task-specific investigation plan. It then iteratively coordinates KG and textual tools to cross-validate structural and semantic evidence, producing a verification verdict with a transparent evidence chain. On independently sampled, balanced test sets constructed from FB15K-237 and Wikidata5M-Ind, SHARP achieves average accuracies of 87.1% and 93.6%, respectively. Controlled comparisons with standard RAG using the same evidence sources, together with ablation studies, further show that the gains arise not merely from external retrieval, but from the combined effects of schema-aware planning, memory augmentation, and iterative hybrid tool use.

cs.AI↗
arXiv2026

SCCL-DT: Semantic-Conflict-Aware Contrastive Learning with Dual-Rule Teacher Distillation for Zero-Shot Chest X-Ray Diagnosis

Contrastive vision-language pre-training supports zero-shot chest X-ray diagnosis, but standard objectives treat every off-diagonal image-report pair in a batch as a negative. In radiology, recurring findings across patients mean that instance mismatch need not imply semantic incompatibility, creating false-negative supervision that we term a semantic conflict. A training-trace audit shows that pair-observations selected by the online mask used during training are enriched for report-derived finding agreement, although this proxy analysis does not establish clinical equivalence. Fixed thresholds can become miscalibrated as similarity distributions evolve, while soft reweighting leaves residual repulsive gradients. We therefore propose Semantic-Conflict-Aware Contrastive Learning (SCCL), which tracks modality-specific similarity distributions with exponential-moving-average (EMA) statistics, derives adaptive thresholds, and hard-masks flagged candidates before softmax normalization. Inclusive (OR) and consensus (AND) rules define two SCCL teachers, whose bidirectional cross-modal rankings are consolidated through standard distillation into a single deployable student, SCCL-DT. Across five public chest X-ray benchmarks, SCCL-DT achieves a mean zero-shot AUC of $0.850$, compared with $0.837$ for the strongest evaluated baseline in our comparison. Code will be made publicly available soon.

cs.CV↗
arXiv2026

LoopRPT: Reinforcement Pre-Training for Looped Language Models

Looped language models (LoopLMs) perform iterative latent computation to refine internal representations, offering an alternative to explicit chain-of-thought (CoT) reasoning. However, existing reinforcement learning (RL) paradigms primarily target output tokens, creating a structural mismatch with looped architectures whose reasoning unfolds implicitly. In this work, we propose LoopRPT, a reinforcement pre-training framework tailored for LoopLMs. By reframing next-token prediction as a next-token reasoning task, LoopRPT assigns reinforcement signals directly to latent steps using an EMA teacher reference and noisy latent rollouts. This formulation enables RL to directly shape intermediate representations, compressing effective reasoning into fewer iterations. We instantiate LoopRPT on Ouro across multiple model scales. Results show that LoopRPT improves per-step representation quality and achieves Pareto dominance in accuracy-computation trade-offs. Large gains on hard tokens indicate that LoopRPT enhances early-stage reasoning rather than merely encouraging premature exits. Our findings highlight reinforcement pre-training as a principled paradigm for learning efficient latent reasoning in LoopLMs.

cs.CL↗
arXiv2026

EvolvingBrain: An Adaptive Skill System for Multi-modal Agents Self-Evolution in Open Worlds

Multi-modal agents have made significant progress in interacting with open worlds. However, their ability to self-evolve remains limited. Supervised fine-tuning enables imitation but not active experience organization, while outcome-based reinforcement learning promotes exploration yet underuses intermediate trajectory information. Therefore, we propose EvolvingBrain, which uses an adaptive skill system as the brain for agent self-evolution, consisting of two following components. Stratified Skill Self-Evolution: extracts Procedural Patterns and Problematic Patterns from model-specific trajectories, summarizes experience by generating skills, and evolves through multiple interactions with the open world, ultimately forming a Stratified Skill Architecture consisting of Domain, Plan, and Action/Trap Skills, which provides the agent with a multi-granularity knowledge repository and a novel evolution approach. State-Aware Adaptive Execution: summarizes long-horizon interactions into Structured Abstractive Memory and uses it to guide the State-Aware Skill Fusion Strategy, enabling the agent to utilize knowledge according to its current state. Experiments on VAB-Minecraft and DiscoveryWorld demonstrate that EvolvingBrain improves success rates on open-world tasks and exhibits generalization capabilities. Our code is provided in the supplementary materials and will be publicly released in the camera-ready version.

cs.AI↗
arXiv2026

Time-JEPA: Grounding Video World Models with Physical Time Series

Video world models learn how visual environments evolve by predicting missing or future content. However, physical-state information can provide useful context for predicting how environments evolve. Prior work incorporates this information through different mechanisms: domain-specific physical laws can complicate multi-domain training, while supervision on individual frames or frame pairs gives limited attention to how physical state evolves over time. We introduce Time-JEPA, which fine-tunes a video world model using low-dimensional, temporally aligned physical time series as auxiliary supervision. Physical time series connect video representations with physical state at corresponding temporal positions, encouraging the model to preserve how physical state evolves. In multiple domains including autonomous driving, robot manipulation, and human motion, Time-JEPA improves current-state decoding, multi-horizon future-state prediction, and kinematic reconstruction over matched video-fine-tuned controls across both condition and state-variable distribution shifts. Multi-domain training provides aggregate gains over matched single-domain training in all three tasks. External evaluations further suggest that time-series supervision improves sensitivity to physical anomalies and the representation of physical interactions, including in unseen scenarios. Aggregate gains on a second video backbone indicate that the method can be applied to more backbones. These results suggest that physical time series help video world models better understand the physical world.

cs.CV↗
arXiv2026

Proactive Physical AI through Continuous Observation and Timely Intervention

Physical AI is commonly formulated around an explicitly specified task: given a goal or instruction, a system perceives, reasons, and acts. In many real-world settings, however, important tasks emerge from continuously changing world states before a person explicitly formulates them. We study this complementary problem as Proactive Physical AI, where an AI system continuously observes the physical world, identifies situations that warrant intervention, and initiates appropriate actions at the right time. We develop ProAgent, an end-to-end system built around two components: a Jev-style proactive timing model (dubbed StreamingJev) that determines whether and when intervention is needed, and a Response Model that generates responses for people or invokes available device capabilities for physical execution. To support learning at scale, we develop an automated data pipeline that converts videos into supervision for proactive timing. Experiments demonstrate strong proactive performance under both explicit objectives and standing roles, combining more accurate intervention timing with fewer false triggers than the source-backbone baseline. Real-robot evaluations further demonstrate ProAgent's ability to identify emerging needs and translate them into appropriate physical actions.

cs.CV↗
arXiv2026

Room-temperature ferroelectric p-wave magnet

P -wave magnets exhibit odd-parity spin polarization in momentum space while retaining zero net magnetization, offering a promising route toward nonrelativistic spintronics. Previously reported p-wave magnets based on combined time-reversal and lattice-translation symmetry, Tt, have thus far exhibited ordering temperatures below the liquid-nitrogen range. Here, we demonstrate a distinct route to a pristine p-wave magnetism that does not require T t symmetry, and instead is based on incommensurate spin-spiral order. Specifically, the cycloidal magnetic structure of the multiferroic BiFeO3 (BFO) intrinsically realizes p-wave magnetism coexisting with ferroelectric polarization at room temperature. Combining symmetry analysis, density-functional-theory calculations, and circular photogalvanic-effect (CPGE) measurements, we find a large nonrelativistic spin splitting of approximately 100 meV associated with the cycloidal order. The resulting p-wave spin polarization gives rise to a characteristic CPGE response whose sign can be reversibly switched by electrically controlling the cycloid chirality. Our results establish ferroelectric BiFeO3 as a room-temperature platform for electrically switchable p-wave magnetism and provide a route toward voltage-controlled spintronic devices based on parity-breaking magnetic order.

cond-mat.mtrl-sci↗
arXiv2026

Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval

A skill can match a task's topic while conflicting with its resource, procedure, or output requirements. We study this as same-capability risk-exposure retrieval and introduce SameCapRisk-Bench: 890 units and 1,314 query cases across five mechanisms and twelve conflict types. Each unit pairs a skill that meets a query requirement with a same-capability skill that violates it, with evidence for that distinction. The evaluation tests source-task requirements and two kinds of paired queries that reverse which skill fits: changing the requested evidence role or exact output interface while holding the skills fixed. To capture both retrieval success and conflicting exposure, Recall tracks helpful hits, harmful sibling rate (HSR) tracks exposure of the conflicting sibling, and CleanHit requires a helpful hit without that exposure. Four public skill retrievers expose conflicting siblings at HSR@3 of 0.737-0.881 on source-task contracts, compared with 0.099-0.12 on controlled source-role queries. Across the fixed mixture of 1,235 held-out queries, their Recall@3 is 0.903-0.944 and HSR@3 is 0.344-0.393. The conflicting sibling ranks first on 24.8-29.2% of source-task queries for these four retrievers. We also examine what the reranker receives: truncating long skills can remove the passages where the two skills' contracts differ. With the same BGE top-20 candidates, increasing the reranker's input budget from 512 to 4,096 tokens reduces source-task sibling-first errors by 8.27 pp, with an uncertain CleanHit gain.

cs.IR↗
arXiv2026

Strain-engineered long-distance supercurrent in an altermagnetic CrSb based-Josephson junction

Altermagnetic materials, characterized by vanishing net magnetization and momentum-dependent spin splitting, provide a unique platform for realizing unconventional superconducting states without the detrimental stray fields. Here, we demonstrate long-distance Josephson supercurrent transport through epitaxial thin films of the strained altermagnet CrSb. We observe a dissipationless supercurrent across a lateral spacer distance of 150 nm in a CrSb-based Josephson junction, exceeding the conventional spin-singlet coherence length by nearly two orders of magnitude. This supercurrent is further accompanied by a well-defined magnetic-field-induced quantum interference pattern, providing direct evidence for genuine Josephson coupling. Our results reveal altermagnets as a promising route toward generating long-distance supercurrents without macroscopic magnetic stray fields, opening new opportunities for superconducting spintronic applications.

cond-mat.supr-con↗