BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Jiawei Zhou

Jiawei Zhou appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
cond-mat.mtrl-sciComputation and Languagecond-mat.mes-hallComputer VisionMachine LearningArtificial IntelligenceInformation Retrievalphysics.opticscond-mat.softCryptography and Securitymath.APphysics.chem-phphysics.comp-phphysics.ins-det

Catalog footprint

What is connected

20works
14topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

20 published item(s)

preprint2026arXiv

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail and inform the next attempt, and lessons accumulate across cycles. Existing autonomous research systems often model this process as a linear pipeline: they rely on single-agent reasoning, stop when execution fails, and do not carry experience across runs. We present AutoResearchClaw, a multi-agent autonomous research pipeline built on five mechanisms: structured multi-agent debate for hypothesis generation and result analysis, a self-healing executor with a \textsc{Pivot}/\textsc{Refine} decision loop that transforms failures into information, verifiable result reporting that prevents fabricated numbers and hallucinated citations, human-in-the-loop collaboration with seven intervention modes spanning full autonomy to step-by-step oversight, and cross-run evolution that converts past mistakes into future safeguards. On ARC-Bench, a 25-topic experiment-stage benchmark, AutoResearchClaw outperforms AI Scientist v2 by 54.7%. A human-in-the-loop ablation across seven intervention modes reveals that precise, targeted collaboration at high-leverage decision points consistently outperforms both full autonomy and exhaustive step-by-step oversight. We position AutoResearchClaw as a research amplifier that augments rather than replaces human scientific judgment. Code is available at https://github.com/aiming-lab/AutoResearchClaw.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding

Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation beyond end-to-end answer accuracy. We introduce DocScope, a benchmark that formulates long-document QA as a structured reasoning trajectory prediction problem: given a complete PDF document and a question, the model outputs evidence pages, supporting evidence regions, relevant factual statements, and a final answer. We design a four-stage evaluation protocol -- Page Localization, Region Grounding, Fact Extraction, and Answer Verification -- that audits each level of the trajectory independently through inter-stage decoupling, with all judges selected and calibrated via human alignment studies. DocScope comprises 1,124 questions derived from 273 documents, with all hierarchical evidence annotations completed by human annotators. We benchmark 6 proprietary models, 12 open-weight models, and several domain-specific systems. Our experiments reveal that answer accuracy cannot substitute for trajectory-level evaluation: even among correct answers, the highest observed rate of complete evidence chains is only 29\%. Across all models, region grounding remains the weakest trajectory stage. Furthermore, the primary difficulty stems from aggregating evidence dispersed across long distances and multiple document clusters, while an oracle study identifies faithful perception and fact extraction as the dominant capability bottleneck. Cross-architecture comparisons further suggest that activated parameter count matters more than total scale. The benchmark and code will be publicly released at https://github.com/MiliLab/DocScope.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Optimizing Retrieval for RAG via Reinforcement Learning

As retrieval-augmented generation (RAG) becomes more widespread, the role of retrieval is shifting from retrieving information for human browsing to retrieving context for AI reasoning. This shift creates more complex search environments, where relevance is difficult to pre-define. Existing retrievers rely on supervised fine-tuning (SFT) with human labels or synthetic data, resulting in static relevance that struggles to adapt to diverse RAG environments. To address this challenge, we propose R3, a Retrieval framework optimized for RAG through Reinforcement learning (RL). Specifically, we adopt an RL training paradigm that enables the retriever to explore and self-improve within given RAG environments, automating the learning process with minimal manual experimentation or tuning effort. Extensive experiments across diverse tasks demonstrate that R3 improves RAG performance by 5.2% over the original retriever and surpasses state-of-the-art retrievers by 4.9%, while achieving comparable results to LLM-augmented retrieval and RAG systems built on post-trained or instruction-tuned LLMs. It is both efficient and practical, requiring only 4 GPUs and completing training within a single day.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models

Large language models (LLMs) often produce answers with high certainty even when they are incorrect, making reliable confidence estimation essential for deployment in real-world scenarios. Verbalized confidence, where models explicitly state their confidence in natural language, provides a flexible and user-facing uncertainty signal that can be applied even when token logits are unavailable. However, existing verbalized-confidence methods often optimize answer generation and confidence generation jointly, which can cause confidence-alignment objectives to interfere with answer accuracy. In this work, we propose a decoupled and order-aware framework for verbalized confidence calibration. Our method first generates an answer and then estimates confidence conditioned on the fixed question--answer pair, allowing confidence optimization without directly perturbing the answer-generation process. To align confidence with correctness likelihood, we construct a sampling-based surrogate from multiple model completions and optimize rank-based reinforcement learning objectives that encourage responses with higher estimated correctness likelihood to receive higher verbalized confidence. Experiments on reasoning and knowledge-intensive benchmarks show that our method improves calibration and failure prediction performance while largely preserving answer accuracy. These results demonstrate that verbalized confidence can be more reliably aligned by decoupling confidence estimation from answer generation and optimizing the relative ordering of confidence across responses.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Xiaomi EV World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving

This report presents a unified technical system addressing the two core capabilities of world models for autonomous driving: world representation and world generation. For world representation, we propose WorldRec, a feed-forward reconstruction architecture driven by sparse scene queries. WorldRec initializes structured queries in 3D space, leveraging them to aggregate cross-view, cross-temporal features, thereby naturally enforcing spatial consistency across frames and yielding compact yet high-fidelity 3D Gaussian scene representations. For world generation, we propose WorldGen, a two-stage training framework of bidirectional pretraining followed by causal fine-tuning through three progressive stages (Teacher Forcing, ODE distillation, and DMD), enabling high-quality online causal video generation in as few as 4 denoising steps. Building on both modules, we further introduce the JWM, which deeply integrates WorldRec and WorldGen to achieve synergistic gains in generation stability, cross-frame consistency, and visual fidelity, providing a solid foundation for closed-loop simulation, data synthesis, and end-to-end training in autonomous driving.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

GEMv2: Multilingual NLG Benchmarking in a Single Line of Code

Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using leaderboards, but the evaluation choices become sub-optimal as better alternatives arise. This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims. To make following best model evaluation practices easier, we introduce GEMv2. The new version of the Generation, Evaluation, and Metrics Benchmark introduces a modular infrastructure for dataset, model, and metric developers to benefit from each others work. GEMv2 supports 40 documented datasets in 51 languages. Models for all datasets can be evaluated online and our interactive data card creation and rendering tools make it easier to add new datasets to the living benchmark.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Global existence and optimal decay rate of the classical solution to 3-D Radiative Hydrodynamics with and without Heat Conductivity

The classical solution of the 3-D radiative hydrodynamics model is studied in $H^k$-norm under two different conditions, with and without heat conductivity. We have proved the following results in both cases. First, when the $H^k$ norm of the initial perturbation around a constant state is sufficiently small and the integer $k\geq2$, a unique classical solution to such Cauchy problem is shown to exist. Second, if we further assume that the $L^1$ norm of the initial perturbation is small too, the i-order($0\leq i\leq k-2$) derivative of the solutions have the decay rate of $(1+t)^{-\frac 34-\frac i2}$ in $H^2$ norm. Third, from the results above we can see that for radiative hydrodynamics, the radiation can do the same job as the heat conduction, which means if the thermal conductivity coefficient turns to $0$, because of the effect of radiation, the solvability of the system and decay rate of the solution stay the same.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering

To alleviate the data scarcity problem in training question answering systems, recent works propose additional intermediate pre-training for dense passage retrieval (DPR). However, there still remains a large discrepancy between the provided upstream signals and the downstream question-passage relevance, which leads to less improvement. To bridge this gap, we propose the HyperLink-induced Pre-training (HLP), a method to pre-train the dense retriever with the text relevance induced by hyperlink-based topology within Web documents. We demonstrate that the hyperlink-based structures of dual-link and co-mention can provide effective relevance signals for large-scale pre-training that better facilitate downstream passage retrieval. We investigate the effectiveness of our approach across a wide range of open-domain QA datasets under zero-shot, few-shot, multi-hop, and out-of-domain scenarios. The experiments show our HLP outperforms the BM25 by up to 7 points as well as other pre-training methods by more than 10 points in terms of top-20 retrieval accuracy under the zero-shot scenario. Furthermore, HLP significantly outperforms other pre-training methods under the other scenarios.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Inducing and Using Alignments for Transition-based AMR Parsing

Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word alignments. These alignments are learned separately from parser training and require a complex pipeline of rule-based components, pre-processing, and post-processing to satisfy domain-specific constraints. Parsers also train on a point-estimate of the alignment pipeline, neglecting the uncertainty due to the inherent ambiguity of alignment. In this work we explore two avenues for overcoming these limitations. First, we propose a neural aligner for AMR that learns node-to-word alignments without relying on complex pipelines. We subsequently explore a tighter integration of aligner and parser training by considering a distribution over oracle action sequences arising from aligner uncertainty. Empirical results show this approach leads to more accurate alignments and generalization better from the AMR2.0 to AMR3.0 corpora. We attain a new state-of-the art for gold-only trained models, matching silver-trained performance without the need for beam search on AMR3.0.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Photomolecular Effect Leading to Water Evaporation Exceeding Thermal Limit

We report the discovery of photomolecular effect: cleavage of water clusters off surfaces by photons. This effect is demonstrated through surprising absorption of partially wetted hydrogel in the visible spectrum where both water and hydrogel materials' absorption are negligible. Illumination of hydrogel under solar or visible-spectrum light-emitting-diode leads to evaporation rates exceeding the thermal evaporation limit, even in hydrogels without additional absorbers. Measurements of temperature and transmission spectrum of vapor above evaporating surfaces show clear signatures of water clusters. The photomolecular effect happens at liquid-vapor interface due to large electrical field gradients and quadrupole force on molecular clusters. This photomolecular evaporation process might be happening widely in nature, potentially impacting climate and plants growth, and can be exploited for clean water and drying technologies.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Significant reduction in semiconductor interface resistance via interfacial atomic mixing

The contact resistance between two dissimilar semiconductors is determined by the carrier transmission through their interface. Despite the ubiquitous presence of interfaces, quantitative simulation of charge transport across such interfaces is difficult, limiting the understanding of interfacial charge transport. This work employs Green's functions to study the charge transport across representative Si/Ge interfaces. For perfect interfaces, it is found that the transmittance is small and the contact resistance is high, not only because the mismatch of carrier pockets makes it hard to meet the momentum conservation requirement, but also because of the incompatible symmetries of the Bloch wave functions of the two sides. In contrast, atomic mixing at the interface increases the carrier transmittance as the interface roughness opens many nonspecular transmission channels, which greatly reduces the contact resistance compared with the perfect interface. Specifically, we show that disordered interfaces with certain symmetries create more nonspecular transmission. The insights from our study will benefit the future design of high-performance heterostructures with low contact resistance.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Automating Botnet Detection with Graph Neural Networks

Botnets are now a major source for many network attacks, such as DDoS attacks and spam. However, most traditional detection methods heavily rely on heuristically designed multi-stage detection criteria. In this paper, we consider the neural network design challenges of using modern deep learning techniques to learn policies for botnet detection automatically. To generate training data, we synthesize botnet connections with different underlying communication patterns overlaid on large-scale real networks as datasets. To capture the important hierarchical structure of centralized botnets and the fast-mixing structure for decentralized botnets, we tailor graph neural networks (GNN) to detect the properties of these structures. Experimental results show that GNNs are better able to capture botnet structure than previous non-learning methods when trained with appropriate data, and that deeper GNNs are crucial for learning difficult botnet topologies. We believe our data and studies can be useful for both the network security and graph learning communities.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Enhancement and tunability of near-field radiative heat transfer mediated by surface plasmon polaritons in thin plasmonic films

The properties of thermal radiation exchange between hot and cold objects can be strongly modified if they interact in the near field where electromagnetic coupling occurs across gaps narrower than the dominant wavelength of thermal radiation. Using a rigorous fluctuational electrodynamics approach, we predict that ultra-thin films of plasmonic materials can be used to dramatically enhance near-field heat transfer. The total spectrally integrated film-to-film heat transfer is over an order of magnitude larger than between the same materials in bulk form and also exceeds the levels achievable with polar dielectrics such as SiC. We attribute this enhancement to the significant spectral broadening of radiative heat transfer due to coupling between surface plasmon polaritons (SPPs) on both sides of each thin film. We show that the radiative heat flux spectrum can be further shaped by the choice of the substrate onto which the thin film is deposited. In particular, substrates supporting surface phonon polaritons (SPhP) strongly modify the heat flux spectrum owing to the interactions between SPPs on thin films and SPhPs of the substrate. The use of thin film phase change materials on polar dielectric substrates allows for dynamic switching of the heat flux spectrum between SPP-mediated and SPhP-mediated peaks.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Phonon Localization in Heat Conduction

Departures in phonon heat conduction from diffusion have been extensively observed in nanostructures through their thermal conductivity reduction and largely explained with classical size effects neglecting phonon's wave nature. Here, we report localization-behavior in phonon heat conduction due to multiple scattering and interference of phonon waves, observed through measurements of the thermal conductivities of GaAs/AlAs superlattices with ErAs nanodots randomly distributed at the interfaces. Near room temperature, the measured thermal conductivities increased with increasing number of SL periods and eventually saturated, indicating a transition from ballistic-to-diffusive transport. At low temperatures, the thermal conductivities of the samples with ErAs dots first increased and then decreased with an increasing number of periods, signaling phonon wave localization. This Anderson localization behavior is also validated via atomistic Green's function simulations. The observation of phonon localization in heat conduction is surprising due to the broadband nature of thermal transport. This discovery suggests a new path forward for engineering phonon thermal transport.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Ab initio optimization of phonon drag effect for lower-temperature thermoelectric energy conversion

While the thermoelectric figure of merit zT above 300K has seen significant improvement recently, the progress at lower temperatures has been slow, mainly limited by the relatively low Seebeck coefficient and high thermal conductivity. Here we report, for the first time, success in first-principles computation of the phonon drag effect - a coupling phenomenon between electrons and non-equilibrium phonons - in heavily doped region and its optimization to enhance the Seebeck coefficient while reducing the phonon thermal conductivity by nanostructuring. Our simulation quantitatively identifies the major phonons contributing to the phonon drag, which are spectrally distinct from those carrying heat, and further reveals that while the phonon drag is reduced in heavily-doped samples, a significant contribution to Seebeck coefficient still exists. An ideal phonon filter is proposed to enhance zT of silicon at room temperature by a factor of 20 to around 0.25, and the enhancement can reach 70 times at 100K. This work opens up a new venue towards better thermoelectrics by harnessing non-equilibrium phonons.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Ab initio study of electron-phonon interaction in phosphorene

The monolayer of black phosphorous, or phosphorene, has recently emerged as a new 2D semiconductor with intriguing highly anisotropic transport properties. Existing calculations of its intrinsic phonon-limited electronic transport properties so far rely on the deformation potential approximation, which is in general not directly applicable to anisotropic materials since the deformation along one specific direction can scatter electrons traveling in all directions. We perform a first-principles calculation of the electron-phonon interaction in phosphorene based on density functional perturbation theory and Wannier interpolation. Our calculation reveals that 1) the high anisotropy provides extra phase space for electron-phonon scattering, and 2) optical phonons have appreciable contributions. Both effects cannot be captured by the deformation potential calculations.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Limiting efficiencies of solar energy conversion and photo-detection via internal emission of hot electrons and hot holes in gold

We evaluate the limiting efficiency of full and partial solar spectrum harvesting via the process of internal photoemission in Au-semiconductor Schottky junctions. Our results based on the ab initio calculations of the electron density of states (e-DOS) reveal that the limiting efficiency of the full-spectrum Au converter based on hot electron injection is below 4%. This value is even lower than previously established limit based on the parabolic approximation of the Au electron energy bands. However, we predict limiting efficiency exceeding 10% for the hot holes collection through the Schottky junction between Au and p-type semiconductor. Furthermore, we demonstrate that such converters have more potential if used as a part of the hybrid system for harvesting high- and low-energy photons of the solar spectrum.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Generalized two-temperature model for coupled phonon-magnon diffusion

We generalize the two-temperature model [Sanders and Walton, Phys. Rev. B, 15, 1489 (1977)] for coupled phonon-magnon diffusion to include the effect of the concurrent magnetization flow. Working within the framework of Boltzmann transport equation, we derive the constitutive equations for coupled phonon-magnon transport driven by gradients of both temperature and external magnetic fields, and the corresponding conservation laws. Our equations reduce to the original Sanders-Walton two-temperature model under a uniform external field, but predict a new magnon cooling effect driven by a non-uniform magnetic field in a homogeneous single-domain ferromagnet. We estimate the magnitude of the cooling effect in yttrium iron garnet, and show it is within current experimental reach. With properly optimized materials, the predicted cooling effect can potentially supplement the conventional magnetocaloric effect in cryogenic applications in the future.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Significant reduction of lattice thermal conductivity by electron-phonon interaction in silicon with high carrier concentrations: a first-principles study

Electron-phonon interaction has been well known to create major resistance to electron transport in metals and semiconductors, whereas less studies were directed to its effect on the phonon transport, especially in semiconductors. We calculate the phonon lifetimes due to scattering with electrons (or holes), combine them with the intrinsic lifetimes due to the anharmonic phonon-phonon interaction, all from first-principles, and evaluate the effect of the electron-phonon interaction on the lattice thermal conductivity of silicon. Unexpectedly, we find a significant reduction of the lattice thermal conductivity at room temperature as the carrier concentration goes above 1e19 cm-3 (the reduction reaches up to 45% in p-type silicon at around 1e21 cm-3), a range of great technological relevance to thermoelectric materials.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Local Structure Matching Driven by Joint-Saliency-Structure Adaptive Kernel Regression

For nonrigid image registration, matching the particular structures (or the outliers) that have missing correspondence and/or local large deformations, can be more difficult than matching the common structures with small deformations in the two images. Most existing works depend heavily on the outlier segmentation to remove the outlier effect in the registration. Moreover, these works do not handle simultaneously the missing correspondences and local large deformations. In this paper, we defined the nonrigid image registration as a local adaptive kernel regression which locally reconstruct the moving image's dense deformation vectors from the sparse deformation vectors in the multi-resolution block matching. The kernel function of the kernel regression adapts its shape and orientation to the reference image's structure to gather more deformation vector samples of the same structure for the iterative regression computation, whereby the moving image's local deformations could be compliant with the reference image's local structures. To estimate the local deformations around the outliers, we use joint saliency map that highlights the corresponding saliency structures (called Joint Saliency Structures, JSSs) in the two images to guide the dense deformation reconstruction by emphasizing those JSSs' sparse deformation vectors in the kernel regression. The experimental results demonstrate that by using local JSS adaptive kernel regression, the proposed method achieves almost the best performance in alignment of all challenging image pairs with outlier structures compared with other five state-of-the-art nonrigid registration algorithms.

0 citations0 reviewsNo code linkedOpen access