Strongly Correlated Electrons
Probing the electronic structure of $\mathrm{UTe}_2$ with ARPES and high-energy spectroscopy
Shin-ichi Fujimori
$\mathrm{UTe}_2$ has emerged as one of the most intensively studied strongly correlated materials in recent years owing to its unconventional superconductivity and the possible realization of a
spin-triplet, topologically nontrivial pairing state. A central open issue concerns the nature of the $\mathrm{U}\,5f$ electrons and their participation in low-energy quasiparticle states. In this review, we summarize recent spectroscopic studies of $\mathrm{UTe}_2$ using momentum-resolved angle-resolved photoemission spectroscopy (ARPES) and element- and configuration-sensitive X-ray probes, including X-ray absorption spectroscopy (XAS), X-ray absorption near-edge structure (XANES), X-ray
magnetic circular dichroism (XMCD), resonant X-ray emission spectroscopy (RXES), and resonant inelastic X-ray scattering (RIXS). A key finding is the pronounced technique dependence of the inferred electronic structure. We synthesize the present spectroscopic picture by integrating these results with modern electronic-structure calculations such as density functional theory plus dynamical mean-field theory (DFT+DMFT). These findings support an intermediate-valence ground state with significant admixture of $5f^2$ and $5f^3$ configurations in $\mathrm{UTe}_2$, and they delineate key experimental and theoretical
benchmarks needed to connect the normal-state electronic structure to the superconducting mechanism.
Read the full abstract ▾
Artificial Intelligence
JudgeProfile: Understanding and Steering Subjectivity in LLM Judges
Qi Cao, Kangning Liu, Xuan Kan et al. (+10 more)
LLM judges are inherently subjective, often favoring different responses in pairwise comparison when neither option is objectively wrong. To study this subjectivity, we introduce JudgeProfile, a framework that dissects LLM evaluation into perception (how a judge compares two responses across specific attributes like clarity, correctness, and detail) and prioritization (how much each attribute influences the final choice). We curate SubjectiveSet, a
dataset of 50,013 response pairs from 17 public data sources, evaluated by 21 LLM judges across 87 attributes. We find a hidden consensus in perception: judges frequently agree on attribute judgments even when their overall choices diverge. Building on this separation, we first characterize each judge's prioritization using attribute weights estimated from its own overall choices. These weights differ across judges even when estimated from the same attribute judgments. We then learn new weights from reference labels to adapt their decisions to a target evaluation standard. Reweighting perceived attributes improves average held-out agreement with reference labels from 66.48% to 71.97%, outperforming fine-tuning and rubric prompting. Our findings show that understanding and steering the subjectivity of LLM judges requires
attention not only to what they perceive, but also to how they prioritize it.
Read the full abstract ▾
All authors Qi Cao, Kangning Liu, Xuan Kan, Shunwen Tan, Yang Pei, Dake Chen, Yatai Ji, Zixuan Ye, Yuanpeng Tu, Daniel Li, Junbiao Tang, Pengtao Xie, Zihao He
Machine Learning
When Is Coarse Supervision Worth It? Cost-Aware Learning under Unknown Aggregation
Jianyu Xu, Smriti Jha, Aarti Singh et al. (+1 more)
Modern learning systems often acquire supervision at multiple resolutions, trading annotation cost against information content. We study cost-aware two-resolution learning, where expensive fine labels reveal a vector response and cheaper coarse labels reveal a scalar aggregate formed with unknown weights, while the target remains the full response. The challenge is that unknown aggregation changes which directions coarse data can identify, so the value of coarse supervision depends jointly on cost, noise, and identification. We characterize this information geometry and develop an estimate-and-track policy that learns the aggregation rule and tracks the optimal resolution mix. We derive a closed-form break-even condition for coarse supervision and prove that the online policy attains the optimal leading cumulative-risk coefficient, with a matching local asymptotic minimax lower bound. Synthetic experiments support the predicted all-fine/mixed transition, show the online learner approaching the oracle-share
benchmark, and demonstrate a finite-budget gain over all-fine acquisition when coarse supervision is sufficiently favorable. Our results provide a principled way to balance information and annotation cost across supervision resolutions.
Read the full abstract ▾
All authors Jianyu Xu, Smriti Jha, Aarti Singh, Bryan Wilder
Mesoscale and Nanoscale Physics
Interlayer coupling between twisted graphenes through atomically-precise barriers
Yueyang Wang, Ben Fuller, Hongxia Xue et al. (+5 more)
Understanding and controlling interlayer coupling in van der Waals (vdW) materials is crucial for engineering novel electronic phenomena, including correlated states, topological phases, and superconductivity. Twisted
bilayer graphene (TBG) offers a highly tunable platform to explore how interlayer orientation and separation influence
quantum transport and moiré physics. Here, we introduce a method for achieving precise, atomic-scale control of interlayer coupling in TBG using dual-gated devices separated by ultrathin, thickness-tunable hBN spacers. This approach enables systematic control of interlayer interactions, demonstrating that the critical displacement field required for electron-hole
bilayer behavior decreases as the layer separation increases at a fixed twist angle. Remarkably, at small twist angles, moiré-related side peaks persist even when layers are separated by tetralayers of hBN (approximately 1.3 nm), indicating robust interlayer band hybridization. By combining atomic-layer-precise control of interlayer coupling with independent twist angle tunability, our platform opens new avenues for discovering novel moiré physics governed by engineered interlayer coupling and moiré patterns.
Read the full abstract ▾
All authors Yueyang Wang, Ben Fuller, Hongxia Xue, Tianyu Zhang, Kenji Watanabe, Takashi Taniguchi, Vladimir Fal'ko, Dong-Keun Ki
Quantum Physics
Quantum Fidelity Landscape-Guided Prior Calibration for Single-Circuit QGAN Image Generation
Xue Yang, Rigui Zhou, Dax Enshan Koh et al. (+5 more)
Quantum Generative
Adversarial Networks (QGANs) have emerged as representative generative models in the Noisy Intermediate-Scale
Quantum (NISQ) era and have attracted increasing
attention in
quantum machine learning. However, most existing QGAN methods rely on patch-based decomposition strategies, which weaken the global consistency of generated images and increase
quantum resource overhead. In this work, we investigate a simpler approach: pixel-level, end-to-end image generation using a single-
quantum-
circuit QGAN. By analyzing the structural matching relationship between the
quantum prior and the target data distribution in
Hilbert space, we provide a new theoretical perspective for understanding the training behavior of naive end-to-end QGANs. Specifically, we introduce the
Quantum Fidelity Landscape (QFL), defined as the pairwise-fidelity structure induced by an ensemble of
quantum states and preserved under shared
unitary transformations of the
quantum generation process. We show that, under a fixed Lipschitz readout, this invariant imposes a one-sided bound on decoded sample separation, motivating calibration of the prior-induced QFL before
adversarial training. To validate this theoretical insight, we propose BasicQGAN, a QGAN framework incorporating
quantum prior calibration. Before
adversarial optimization, BasicQGAN aligns the prior-induced QFL with the data-induced QFL. Experimental results on small-scale grayscale image
datasets show that BasicQGAN achieves stable and effective end-to-end pixel-level image generation while requiring fewer
qubits and trainable parameters than representative patch-based
quantum generators. Furthermore, experiments with different initial
quantum-state ensembles show that QFL-calibrated ensembles achieve better generative performance.
Read the full abstract ▾
All authors Xue Yang, Rigui Zhou, Dax Enshan Koh, Siong Thye Goh, Yitao Tang, ShiZheng Jia, Young-Wook Cho, Hongyu Chen
Computational Engineering
Interpolating Neural Operator (INO): A Data-Free and Efficient Approach for Learning PDE Solution Operators
Jiachen Guo, Ye Lu, Naichen Shi et al. (+2 more)
Neural operators have become a popular approach to approximate the solution operators of parametric partial differential equations (PDEs). However, existing neural operators either require a large amount of simulation data or a long physics-informed training on GPUs, and they cannot tell how accurate an individual prediction is. In this paper, we propose the Interpolating Neural Operator (INO), a data-free interpolating neural network that is trained directly on the weak form of the PDE. In INO, the Karhunen-Loève coordinates of the input field are treated as additional inputs together with the spatial coordinates, and each input is approximated by a C-HiDeNN sub-network whose trainable parameters are nodal values. Since the network is multilinear in its parameters, training reduces to a sequence of one-dimensional linear solves by greedy alternating least squares. As a result, INO trains on one CPU core and predicts a new solution in microseconds. For coercive problems, the total error of every prediction is bounded by a computable residual bound that requires no reference solution, and the same bound applies to the predictions of other methods that satisfy the boundary conditions exactly. Before each prediction, INO checks whether the leading coordinates of the input lie within the range on which it is trained, and inputs outside this range can be passed to a conventional solver or to an INO trained on a wider range. INO is compared with physics-informed FNO and DeepONet on different
benchmarks. INO is the most accurate model on most of these problems, by 15$\times$ on two-dimensional Helmholtz at $65^2$ and 53$\times$ on the
diffusion-reaction
benchmark, and on the one- and two-dimensional problems its training on one CPU core takes 3-80$\times$ less time than the physics-informed baselines on one GPU.
Read the full abstract ▾
All authors Jiachen Guo, Ye Lu, Naichen Shi, Thomas J.R. Hughes, Wing Kam Liu
Computation and Language
Lost in Conversation or Lost in Translation? Diagnosing Multi-Turn Degradation in RAG
Pranav Handa and Ariful Azad
When conversing with large
language models (LLMs), users often begin with a simple question and build towards a multi-hop question through follow-up turns.
Retrieval-augmented generation (RAG) and its graph-based variant (GraphRAG) have become the dominant approaches for grounding LLM responses in external evidence, yet both are evaluated almost exclusively on single-turn, fully specified queries. We systematically investigate this evaluation mismatch through a large-scale simulation study. Building on prior work on multi-turn LLM evaluation, we transform questions from multi-hop question answering (QA)
benchmarks into underspecified conversations and evaluate ten LLM assistants with eight
retrieval systems across 1.5 million simulated conversations. Our findings reveal that multi-turn interaction causes widespread performance degradation, incurring relative performance drops of up to 21% and increasing unreliability by 47%, making RAG systems simultaneously less accurate and less reliable. We identify two distinct failure modes behind this degradation. Systems are either lost in translation, where conversational rephrasing distorts the
retrieval query, or lost in conversation, where
retrieval succeeds but the LLM fails to synthesize evidence distributed across turns.
Read the full abstract ▾
Chemical Physics
Electronic excitation spectra and recovery of excited states with neural network wave functions
Xiaoyu Zhang, Weizhong Fu and Yixiao Chen
Accurate electronic spectra require both a flexible description of electron correlation and a tractable treatment of the many states contributing to the response. We combine neural network wave functions with the Lorentz integral transform to calculate electronic spectra directly in continuous coordinates, without truncation error from a fixed one-electron basis and with
polynomial computational cost per optimization step. Instead of constructing a prescribed set of excited states, the method solves an inhomogeneous Schrödinger equation at a chosen complex energy. This formulation gives access, in principle, to the entire spectrum coupled to a perturbation, including bound excitations and the ionization continuum, without explicitly determining all lower-lying eigenstates. A finite imaginary energy controls the resolution and keeps the response square integrable. Near an isolated bound excitation, the normalized response also recovers the corresponding eigenstate as the width tends to zero. A helium application illustrates the extraction of an excitation energy and oscillator strength. The formulation provides a route from neural descriptions of electronic correlation to spectra beyond a small
manifold of low-lying states.
Read the full abstract ▾
Machine Learning
Learned Queries and Keys Are All You Need: Replacing the Value Projection with Structured Transforms
Ene Meco, Emadeldeen Hamdan and A. Enis Cetin
To reduce the number of parameters and cache
memory requirements of
transformers we introduce dual-headed
transformers instead of three heads. We studied Walsh-Hadamard Transform (WHT), Discrete Cosine Transform (DCT), Discrete
Fourier Transform, filterbank based Shearlet Transform, and Multiplication-Avoiding (MA) operators to construct dual heads. We combine spatial patches and their orthogonal transforms (or Shearlet and MA operators) in a structure similar to the
attention block. We obtained better results than triple headed
transformers in ImageNet. Extensive simulation examples are presented.
Read the full abstract ▾
Earth and Planetary Astrophysics
High-CO2 Climates and Observables in the Outer Habitable Zone
Daria Pidhorodetska, Edward W. Schwieterman, Thomas J. Fauchez et al. (+1 more)
The habitable zone (HZ) is a fundamental concept used to guide our search for temperate
exoplanets with stable surface
liquid water that would sustain remotely detectable biosignatures. So far, most advanced 3D
climate studies and prospective spectral simulations of HZ
planets have focused on inner HZ
planets that receive
stellar radiation similar to Earth and would consequently maintain relatively low (e.g., hundreds of parts per million) atmospheric CO2. Here, we present a systematic investigation of outer HZ (OHZ)
planets, which require high CO2 for habitability, using the 3D Generic Planetary
Climate Model (PCM). Our 3D
climate results are compared with previous 1D predictions that show strong agreement between models. Simulated spectra of the modeled
planets indicate that high overlying CO2 levels affect remote signatures of habitability. We also determine substantial spectral differences that would distinguish habitable versus nonhabitable high-CO2 worlds with future direct-imaging observations for
solar analogs and with transmission and emission spectroscopy for M
dwarfs. Our results demonstrate that 3D models that include CO2 condensation are necessary to understand the potential planetary habitability and spectral impacts of clouds on terrestrial worlds in the OHZ.
Read the full abstract ▾
All authors Daria Pidhorodetska, Edward W. Schwieterman, Thomas J. Fauchez, Martin Turbet
High Energy Physics (Phenomenology)
Sensitivities of Long and Medium Baseline Experiments to Sterile Neutrinos and Non-Standard Interactions
Sambit Kumar Pusty, Trisha Guin and Rukmani Mohanta
In this work, we present for the first time, the simultaneous analysis of the non-standard
neutrino interactions (NSI) and a light sterile
neutrino in the 3+1 framework for the future long- and medium-baseline experiments DUNE and MOMENT, respectively. We show that treating the two sectors separately yields over optimistic sensitivities. The simultaneous presence of sterile-
neutrino mixing and complex NSI weakens the $|\varepsilon_{e\mu}|$ sensitivity by a factor of $\sim (2-3)$ with the dominant degradation associated with the additional parameter freedom in the
flavor-changing NSI sector. DUNE alone fails to achieve $5\sigma$ CP-violation discovery, once NSI phases are marginalized over. The DUNE+MOMENT combination recovers $>5\sigma$ sensitivity over a wide range of $\delta_{\rm CP}$ space, constrains $\sin^2\theta_{24}\lesssim10^{-2}$ and $|\varepsilon_{e\mu}|\lesssim0.025$ at $95\%$~C.L., and resolves degeneracies that are intractable for either experiment alone. Our results establish that a multi-baseline strategy combining matter-rich and near-
vacuum baselines is necessary for robust parameter extraction in the simultaneous presence of two new physics scenarios. It is also important to perform simultaneous new physics analyses to reliably interpret future precision
neutrino oscillation data.
Read the full abstract ▾
Machine Learning
Know Thyself, Teach Thyself: Internal Information Flow for Selective Self-Distillation
Rui Wang, Ruijie Wang, Bo Chen et al. (+2 more)
Self-
distillation turns knowledge
distillation into a closed learning loop and offers a path toward recursive self-improvement. Without an external teacher, however, the model must determine both what information can improve its supervision and which induced changes should be learned. Existing methods typically improve teacher-generated data or select training examples in isolation, leaving the information transferred between these stages unmeasured. We introduce InFlow, a
retrieval-guided on-policy self-
distillation framework that models this process as potential-to-realized information flow. InFlow first retrieves potentially informative sources using certainty-calibrated hidden-state trajectories, then measures their realized effect through the Jensen–Shannon divergence between the teacher's initial and
retrieval-conditioned answer beliefs. Examples with larger belief shifts are selected for on-policy
distillation. Our analysis formalizes the information optimized by
retrieval and selection and relates the answer-level shift to the teacher–student
distillation gap. Across four open-weight
language models and three knowledge domains, InFlow achieves the strongest cross-model average among the compared selection methods, with ablations supporting both stages of the framework. Our code is available at https://github.com/1240148048/INFLOW.
Read the full abstract ▾
All authors Rui Wang, Ruijie Wang, Bo Chen, Jiangxuan Long, Yingyu Liang
Quantum Physics
Optimized Randomized Hamiltonian Simulation via Average-Error Analysis
Hayata Morisaki and Keisuke Fujii
Hamiltonian simulation is a central application of
quantum computing. Randomized
Hamiltonian simulation approximates the target dynamics by sampling
quantum circuits and often allows simpler
circuit implementations. We develop a framework for randomized
Hamiltonian simulation in which
Hamiltonian terms are sampled with arbitrary probabilities and the corresponding short-time evolutions are implemented sequentially. The leading channel error relative to ideal time
evolution is governed by the variance of the sampled generators. Minimizing the variance-based upper bound on the worst-case error recovers qDRIFT, a leading randomized
Hamiltonian simulation
algorithm that samples terms in proportion to their operator norms. For typical input states, however, this sampling distribution need not be optimal. Minimizing Haar-averaged error bounds instead yields sampling probabilities proportional to the
Hilbert-Schmidt norms of the terms. This choice can provide smaller average-error bounds than conventional qDRIFT. For
Hamiltonians expressed as sums of Pauli strings, we combine this framework with commuting Pauli grouping to obtain smaller error bounds than conventional qDRIFT at fixed $R_z$ depth. Numerical
benchmarks for the Sachdev-Ye-Kitaev model show error-bound improvement factors consistent with linear scaling in the number of
qubits. For the 108-
qubit FeMoco
Hamiltonian, the error bounds are reduced by a factor of about 5.65. These results establish average-error optimization as a practical design principle for randomized
Hamiltonian simulation.
Read the full abstract ▾
Computer Vision
AESplat: Advancing Pose-Free Feed-Forward 3D Gaussian Splatting via Decoupled Appearance Modeling
Shiwei Ren, Zhiang Liu, Yongchun Fang et al. (+1 more)
Pose-free feed-forward 3D Gaussian Splatting (3DGS) has demonstrated remarkable potential for generalized novel view synthesis. However, existing methods typically predict Gaussian appearance attributes represented by spherical harmonics (SH) in the same manner, overlooking the fundamental distinction between view-independent and view-dependent appearance, which results in suboptimal rendering quality. In this paper, we present AESplat, a novel and general framework for pose-free feed-forward 3DGS that introduces an effective decoupled appearance modeling strategy based on an analysis of SH, enabling higher-quality rendering. Specifically, AESplat directly derives the zeroth-order SH coefficient, which represents the base view-independent appearance component, from the input images without training. The higher-order SH coefficients are subsequently predicted by a shallow multilayer perceptron equipped with two efficient 3D-aware inductive biases to model view-dependent appearance variations. Extensive experiments across multiple
datasets demonstrate that our method significantly outperforms state-of-the-art approaches, achieving a $0.8$ dB improvement in PSNR over the pose-free method NAS3R and a $1.1$ dB improvement over the pose-required method DepthSplat on the RealEstate10K
dataset. Project page: https://aesplat.github.io/.
Read the full abstract ▾
All authors Shiwei Ren, Zhiang Liu, Yongchun Fang, Hongwei Chen
Machine Learning
Normalize-Then-Precondition: A Hierarchical Approach to Marginal Scale and Interaction Geometry for LLM Training
Zixuan Gong, Zeyu Gan, Jiaye Teng et al. (+1 more)
Matrix optimizers have emerged as a promising direction, with
Muon standing out as a prominent design. Revisiting
Muon through its full-Gram representation, we observe that it jointly processes marginal-scale and interaction information. This opens an alternative way to organize
geometric information hierarchically, motivating the Normalize-Then-Precondition framework. Specifically, it first uses diagonal-Gram information to construct a marginally normalized update, then applies spectral preconditioning to its directional interaction geometry. Building on this framework, we develop NormPre with NormPre-G and NormPre-L adopting global and localized spectral preconditioning, grounded in spectral-norm steepest descent and a regularized formulation followed by leading mode selection, respectively. To enable large-scale training, NormPre-G uses Newton-Schulz iterations and NormPre-L employs randomized sketching to approximate the leading interaction eigenspace. Theoretically, we establish $\mathcal{O}(T^{-1/2})$ convergence guarantees for simplified versions of NormPre. Across extensive pretraining experiments on GPT-2 Small, LLaMA and Qwen3, both variants consistently outperform AdamW,
Muon and MANO under matched training budgets. Further efficiency and spectral analyses reveal the complementary strengths of two variants and characterize their performance-efficiency trade-off. We open-source our code through a GitHub repository at https://github.com/zx-gong/NormPre.
Read the full abstract ▾
All authors Zixuan Gong, Zeyu Gan, Jiaye Teng, Yong Liu
Computation and Language
Video2Skill: From Streaming Experience to Reusable Embodied Skills
Jianshu Zhang, Ce Zhang, Xiyuan Yang et al. (+6 more)
Manipulation behaviors vary widely across objects and scenes, but they share a small set of reusable skills, and planning with these skills helps
embodied agents generalize to new tasks. Yet an
agent can only plan with skills it knows. Recovering skills from observed experience, the inverse of planning, builds this knowledge over time and yields skill data for training future
agents.
Vision-
Language Models (VLMs) describe individual manipulation events well, but can they organize a stream of events into reusable skills? We formulate this problem as Streaming
Embodied Skill Discovery (SESD): a model watches
videos in sequence and maintains a persistent skill library that shapes its later decisions. To systematically measure this ability, we introduce
Video2Skill, a
benchmark that covers
robot tabletop manipulation and human kitchen activity and tests three core capabilities: (i) locating manipulation events in time, (ii) grouping events of the same transformation, and (iii) deciding when to reuse an existing skill or create a new one. Across 19 open-source VLMs, many models group events at near-chance level, and scale does not consistently help. Their errors depend on how perception and library updates are coupled: joint models merge distinct transformations into one skill, while models that update the library from text descriptions duplicate recurring ones. Supervised fine-tuning, including our counterfactual library-state rebalancing (CLaRe), improves grouping but exposes a deeper bottleneck: trained models consolidate familiar skills yet rarely expand the library. Their libraries stall below half the reference size, and transformations unseen in training are located in time but almost never given a new skill. Recognizing when existing skills are insufficient thus emerges as the central challenge.
Read the full abstract ▾
All authors Jianshu Zhang, Ce Zhang, Xiyuan Yang, Chenwei Xu, Haoran Lu, Yijiang Li, Yaqi Xie, Katia P. Sycara, Han Liu
Optics
Co-design of Silicon Microring Modulator beyond 200 Gb/s per Lane: Device Physics, Operating Point, and Compact Models for Scale-Up and Scale-Out Optical I/O
Zhihong Huang, Yuan Yuan, Yiwei Peng et al. (+3 more)
Optical input/output (I/O) supports high-bandwidth communication between processors in artificial intelligence (AI) systems. Depletion-mode silicon microring modulators offer compact footprints, wavelength multiplexing and femtojoule-scale junction switching energy per bit. However, as lane rates increase to 200~Gb/s and beyond, a digital signal processor (DSP) performing equalization and forward-error correction can consume up to half of the optical module power. We analyze the junction and cavity physics of silicon microring modulators, relating modulation efficiency, capacitance, optical loss and coupling to bandwidth and drive requirements to guide device optimization above 200~Gb/s per lane.
Laser detuning and optimal operating points are examined by distinguishing maximum static slope, static and dynamic OMA, and gain–bandwidth product (GBW), including the influence of the junction RC response. The effects of optical self-heating, photocarriers and bias-network voltage droop on the resonance are discussed together with heater tuning and wavelength assignment in DWDM arrays. Cold-resonance design points are calculated from the required hot detuning, link-budget-derived optical power and assumed thermal parameters, with heater reserve and startup acquisition included as design constraints. A compact model of the coupled electrical, optical and thermal dynamics is used to evaluate PAM4 eye diagrams, and a Verilog-A implementation of the model core is provided for
circuit-level simulation.
Read the full abstract ▾
All authors Zhihong Huang, Yuan Yuan, Yiwei Peng, Samuel Palermo, Marco Fiorentino, Raymond G. Beausoleil
Machine Learning
CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference
Wenjin Liu, Chenxi Wang, Yue Lu et al. (+2 more)
Large
language models have achieved significant progress in event
forecasting, yet their probability outputs exhibit systematic calibration bias that varies heterogeneously across different domains and question types, undermining the trustworthiness of probabilistic outputs for decision-making under uncertainty. However, existing calibration methods typically correct probability outputs after prediction is complete, without modeling the structural sources of bias within the prediction process itself. To address this challenge, we decompose probabilistic prediction over causal-temporal hypergraphs into three stages, evidence weighting, evidence aggregation, and source fusion, and propose CHAIN, which designs stage-specific mechanisms to mitigate bias at each stage: (i) modulating the temporal decay function by causal topological distance, (ii) aggregating approximately independent causal chains via Noisy-OR after direction-aware deduplication, and (iii) driving adaptive fusion by causal coverage and directional balance. Experimental results on cross-domain
forecasting benchmarks show CHAIN outperforms existing methods in expected calibration error, Brier score, and accuracy. Our project is available at https://github.com/QwenQKing/Chain.
Read the full abstract ▾
All authors Wenjin Liu, Chenxi Wang, Yue Lu, Zhe Cui, Haoran Luo
Information Retrieval
GRP v0.1 Technical Report
Wenfeng Zhuo, Vincent Xue, Charles Wei et al. (+19 more)
Industrial recommendation systems rely on multi-stage cascades whose
retrieval, ranking, and serving components are difficult to replace jointly. We present GRP, a generative recommendation framework that combines
retrieval, ranking, and reward modeling in a single encoder-decoder model, and evaluate a progressive path toward end-to-end recommendation. The model generates
multimodal Semantic IDs and scores candidates with a jointly trained ranking module. The frozen ranking module then supplies rewards for reinforcement-learning post-training. We introduce mGRPO, which adds a reference-anchored margin to reward optimization to preserve the likelihood of logged targets. Offline experiments examine history encoding, model capacity allocation, event selection, tokenization, and reward discrimination. Serving optimizations reduce end-to-end
retrieval latency by 69%. Online experiments evaluate the model as a
retrieval source, with early-ranking bypass, and with replacement of weaker sources. In a
retrieval-only comparison, view time increases by 0.46% and shares by 0.77% relative to production. A separate comparison combining bypass and source replacement yields increases of 0.82% in view time and 2.56% in shares, with neutral platform-level guardrails. These results support progressive deployment while identifying remaining gaps in ranking quality and performance across recommendation metrics.
Read the full abstract ▾
All authors Wenfeng Zhuo, Vincent Xue, Charles Wei, Cong Ni, Ruiming Lu, Jiwen Ren, Mo Li, Peng Yang, Xufei Wang, Dongheng Li, Jiacong He, Yi Song, Yufei Fan, Mikhail Obukhov, Yiwen Chen, Yvette Liu, Yin Ye, Chengjie Wu, Mingtao Zhang, Jinchao Ye, Lili Zhang, Chunhui Zhu
Signal Processing
MyoCodec: A Streaming Neural Codec for Electromyography
Jihwan Lee, Kleanthis Avramidis, Junhyeok Lee et al. (+3 more)
Neural codecs encode continuous signals into compact sequences of discrete
tokens, providing an interface for efficient transmission, storage, and
token-based sequence modeling. This paradigm has been widely adopted in modern
speech and audio frameworks; however, the biosignal domain still lacks a neural codec designed specifically for low-bitrate streaming and generalization across diverse downstream tasks. We present MyoCodec, a streaming neural codec designed for electromyography (EMG). Inspired by recent neural audio codecs, MyoCodec combines causal
Transformers with residual vector quantization to encode continuous EMG signals into different levels of EMG representations spanning from continuous latent features to discrete
tokens operating at 50 Hz. Trained on twelve public EMG
datasets, MyoCodec achieves favorable performance in both intrinsic codec quality and representative downstream tasks, including typing (emg2qwerty), hand-pose (emg2pose),
speech decoding (emg2
speech), and
speech-to-EMG synthesis (
speech2emg). Across these tasks, MyoCodec exhibits strong performance against prior models while providing a compact and causal EMG representation. During streaming inference, it requires compute time of only 0.482 ms for each 20 ms frame, enabling real-time streaming. Also, the discrete
token representation provided by MyoCodec has the potential to support integration into
language-model based approaches, creating a path toward LLM-based interactive systems, where tokenized EMG representations are directly processed into such
language or
speech models. Code and model weights are released.
Read the full abstract ▾
All authors Jihwan Lee, Kleanthis Avramidis, Junhyeok Lee, Tiantian Feng, Najim Dehak, Shrikanth Narayanan
Machine Learning
Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition
Hada Melino Muhammad, Luan Pham, Laure Barrière et al. (+3 more)
Identifying the root cause of an anomaly among hundreds of sensors is critical for preventing safety incidents and costly downtime in complex monitored systems. Existing studies evaluate root cause analysis (RCA) methods using top@k accuracy. We show that this metric has a fundamental blind spot: it conflates two failure modes,
retrieval failure, where the true cause is never considered, and reranking failure, where it is considered but ranked too low. In this work, we introduce a
retrieval-reranking decomposition and audit four well-known
benchmarks to expose this blind spot. Our experiments show that, on
benchmarks with complex faults, statistical baselines mis-rank the true cause 79-100% of the time, and graph-based methods never clearly beat the best statistical baseline, whether their causal graphs are learned on short fault windows, on retrieved candidate pools guaranteed to contain the cause, or on multi-day normal-operation data. Meanwhile, on simple
benchmarks where faults manifest significantly at their origin,
retrieval is nearly solved (98-100%). Guided by the decomposition, we build a two-stage pipeline combining a multi-signal retriever with an LLM reranker that, as one fixed configuration, matches or exceeds the best baseline's top@1 accuracy on all six
benchmark suites (by up to +12 points), with no causal graph or labeled data required. When all methods rank the same retrieved candidates with the true cause guaranteed present, adding a short system-description document lets the reranker lead the best baseline by +7 to +18 points on every
benchmark. Code is available at https://github.com/cruiseresearchgroup/DecompRCA.
Read the full abstract ▾
All authors Hada Melino Muhammad, Luan Pham, Laure Barrière, Sachin Shetty, Leonardo Pulga, Flora D. Salim
Computer Vision
When Semantics Matter: Reliability-Aware Semantic-Rhythm Control for Co-Speech Gesture Generation
Zhirui Xing, Long Ye, Kaige Li et al. (+2 more)
Co-
speech gesture generation aims to synthesize natural gestures that are both temporally synchronized with
speech and semantically consistent with the spoken content. Although recent methods can generate rhythmically plausible motions, they often rely heavily on acoustic prosody while underutilizing textual semantics, especially when semantic annotations are incomplete, noisy, or unavailable. Consequently, the generated gestures may follow
speech rhythm while failing to express the intended semantics. To address this problem, we propose a reliability-aware semantic-rhythm control framework for co-
speech gesture generation. We first learn a discrete motion prior that represents continuous gestures in a compact and structured motion-code space. We then introduce a dual-branch semantic contribution estimation mechanism consisting of a full
multimodal branch and an audio-only branch. Their distributional discrepancy is formulated as conditional information gain to quantify how much textual semantics changes the predicted motion. Based on this estimate, a controllable semantic-rhythm objective selectively strengthens semantic guidance in content-relevant segments while limiting unnecessary semantic intervention in rhythm-dominant segments. Furthermore, we treat background noise as an acoustic reliability condition and introduce noise-conditioned feature modulation together with beneficial latent perturbation to improve generation robustness under realistic acoustic environments. Experiments on
benchmark datasets demonstrate that the proposed framework achieves a favorable balance among semantic expressiveness, rhythmic synchronization, motion diversity, and robustness, enabling reliable and controllable co-
speech gesture generation.
Read the full abstract ▾
All authors Zhirui Xing, Long Ye, Kaige Li, Ziyi Xu, Ming Meng
Computation and Language
ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context
Jianshu Zhang, Keliang Wu, Chengxuan Qian et al. (+6 more)
Embodied agents now take on ever longer tasks. For long tasks, knowing only whether a task finally succeeds or fails says little; the steps along the way matter. Progress Reward Models (PRMs) score how far a task has come at every step, and serve as dense rewards, verifiers and monitors. Yet in long tasks the current frame alone often cannot tell how far the task has come, because progress depends on what happened before. We call this problem context-dependent progress estimation. Existing
benchmarks on progress estimation mostly focus on short tasks whose progress can be read from the current observation, and whether PRMs can estimate progress when context is needed remains underexplored. We therefore build ContextProgress-Bench, with 24 manipulation tasks for 120 episodes. The
benchmark covers three settings: (i) State Recall, where information needed for progress appeared earlier but is not in the current frame; (ii) Sequence Tracking, where steps follow a fixed order, so progress requires knowing which steps are done and which comes next; and (iii) Recurrence Disambiguation, where look-alike frames sit at very different progress. We then run a paired diagnosis: each PRM keeps the same input format in both runs, and in one run its instruction integrates the right context. Even PRMs that read the entire history get lost in estimating progress, yet with the right context the same five models cut their progress error by 77-82%.
Embodied PRMs are thus not incapable of progress estimation, but lost without the right context. We therefore propose ProgressCompass, an autonomous agentic loop that reorients an existing PRM and uses current general-purpose VLMs to supply the context the PRM needs. Wrapped in the loop, the same frozen PRM cuts its progress error by 63% and raises its rank agreement by 76%. With such a compass, PRMs estimate progress far better on longer, more complex tasks.
Read the full abstract ▾
All authors Jianshu Zhang, Keliang Wu, Chengxuan Qian, Xiyuan Yang, Ce Zhang, Ariel Tian, Anbang Liu, Haoran Lu, Han Liu
Machine Learning
MARCO: Multi-Round Agentic Reinforcement for Conditional Molecular Optimization
Shicheng Fang, Yuxin Wang, Zhuo Yang et al. (+6 more)
Molecular optimization is inherently iterative: a candidate is proposed, evaluated against several objectives, and revised while preserving a relationship to the source molecule. Most instruction-following models instead emit one edited molecule, forcing validity, property improvement, and similarity control into a single response. We introduce MARCO, an evaluator-grounded reinforcement-learning framework that trains molecular editors on bounded proposal–feedback–revision trajectories. MARCO aggregates shaped turn rewards into an undiscounted trajectory return for group-relative policy optimization. We evaluate two consequences of this training: Same-1 tests the trained policy under a one-response budget, while Same-5 tests whether the same policy can use verifier feedback when up to five responses are available. Across the three-objective MuMOInstruct
benchmark, three Qwen backbones, and seen/unseen instruction splits, SFT-initialized MARCO obtains the highest product of property success rate and similarity in every reported primary setting. Same-5 further improves the observed score under the tested budget, while four-objective and public-checkpoint experiments test transfer across constraint sets and initialization regimes.
Read the full abstract ▾
All authors Shicheng Fang, Yuxin Wang, Zhuo Yang, Xiaohu Xu, Jiahao Lu, Chuanyuan Tan, Tong Zhu, Yining Zheng, Xipeng Qiu
Materials Science
Polar-Domain Volume as a Unified Descriptor of Transport in Ionic Liquids
Ganesh K. Rajahmundry and Tarak K. Patra
Developing molecular scale structural descriptors that can quantitatively predict the macroscopic transport properties of ionic
liquids remains a longstanding question, owing to the complex interplay between molecular interactions, nanoscale organization, and collective ion dynamics. Here, we use all atom molecular dynamics simulations to establish quantitative structure property relationships between the
equilibrium microstructure and two key transport properties viscosity and ionic conductivity in a series of imidazolium based ILs with chemically distinct anions and varying alkyl chain lengths. While viscosity and ionic conductivity exhibit distinct dependencies on alkyl chain length and anion chemistry, these seemingly different trends largely collapse onto unified correlations when expressed in terms of the mean polar-domain volume. In particular, both transport properties exhibit systematic power-law scaling with the mean polar domain volume fraction, revealing a common structural origin underlying the variations in ion and momentum transport across chemically distinct ILs. These results establish polar-domain volume as a physically motivated molecular-scale descriptor and provide a general structure property framework for connecting nanoscale organization to macroscopic transport properties in ILs.
Read the full abstract ▾
Materials Science
Averaging in thermodynamic dislocation theory: general macroscopically uniform stress and strain states
Khanh Chau Le
The averaging procedure, developed for polycrystalline bars under axially symmetric tension or compression, is extended to arbitrary macroscopically uniform stress and strain states. Starting from the equal probability hypothesis for grain orientations, the mean resolved shear stress and the mean resolved elastic and plastic shear strains are defined as root-mean-square averages over all slip-system orientations. Two exact identities for isotropic orientation averages show that the mean resolved shear stress is proportional to the von Mises equivalent stress, and that the direction of macroscopic plastic flow, obtained from the hypothesis that the plastic slip rate on a system is proportional to the resolved shear stress acting on it, is the stress deviator. The result is an associated $J_2$ flow theory whose hardening law is not fitted but follows from the kinetics of thermally activated dislocation depinning and the
evolution equations for the dislocation density and the effective disorder temperature of thermodynamic dislocation theory, written as rates with respect to time so that arbitrary loading paths can be followed. For torsion the theory yields the torque–twist relation of bars and tubes without the classical reductions to a shear stress–strain curve. The parameters for copper are identified jointly from Hopkinson-bar tension, dynamic compression at room and elevated temperatures, and torque–twist records at several twist rates. One set of material parameters, consistent with the earlier compression-only identification, describes tension, compression and torsion from room temperature to $1173$\,K and from $10$ to $2300$\,s$^{-1}$ to $6$\,% rms over 142 data points; the tension–torsion discrepancy noted by Johnson and Cook is traced to the initial dislocation state of their torsion specimens.
Read the full abstract ▾
Computer Vision
Reprogramming Vision-Language Models via Structured Prompt Reparameterization
Zizhao Li, Chengyi Cai, Mohammed Yaqoob Ansari et al. (+3 more)
Visual reprogramming adapts pretrained models to downstream tasks by modifying their input and output interfaces while keeping the backbone fixed. In
vision-
language models, existing methods mainly rely on intra-class
prompt aggregation and do not explicitly model relationships among classes. However, fine-grained categories often exhibit highly overlapping attribute descriptions and strong inter-class correlation in the text
embedding space, where discriminative cues lie in subtle low-variance components. We propose Reparameterized Inter-Class Visual Reprogramming (RVP), a structured framework that aggregates multiple text
prompts within each class and applies residual correction across classes. We also show that CLIP-based visual reprogramming with input-independent linear output aggregation can be expressed as a linear mapping from frozen image
embeddings to downstream logits, and use this view to design a structured reparameterization that models shared semantic components and class-specific differences. RVP uses only a single visual
prompt and can be reparameterized at inference into a frozen backbone followed by a linear classifier, incurring nearly zero computational overhead. Across 11 few-shot classification
benchmarks and four CLIP backbones, RVP consistently improves over prior visual reprogramming methods with comparable or better inference efficiency.
Read the full abstract ▾
All authors Zizhao Li, Chengyi Cai, Mohammed Yaqoob Ansari, Feng Liu, Joseph West, Kourosh Khoshelham
Artificial Intelligence
MLToolBench: Learning Tool-Augmented Agents for Machine Learning Development
Xin Yu, Lizhu Zhang, Jiamu Bai et al. (+7 more)
Machine learning engineering (MLE)
agents have made substantial progress, but learning through ML experimentation remains costly in time and computation. Synthetic environments reduce these costs while introducing variations in data and experimental settings that require task-specific diagnosis. Access to diagnostic tools alone does not ensure that
agents learn when to use them or how to act on their findings. We introduce ToolMLBench, a suite of executable tools for data inspection, code verification, and experiment diagnosis, together with an SFT and RL pipeline for learning their use. Diagnostic calls acquire evidence whose value depends on subsequent decisions, so final outcomes provide limited guidance on which calls to reinforce. We address this challenge with SPICE, which measures how privileged context changes the likelihood of a sampled tool action and uses this difference as a turn-level reward alongside the final outcome. We train on 80 synthetic tasks and evaluate on 25 in-domain and 10 out-of-domain tasks. Providing tool interfaces and descriptions alone yields inconsistent gains across unadapted models. With the same diagnostic interface, our training pipeline raises in-domain success from 24.8% to 52.4% for Qwen3-8B and from 35.6% to 69.2% for Qwen3.5-35B-A3B. The latter also improves from 31% to 48% out-of-domain, supporting learned diagnostic tool use on held-out sources and targets.
Read the full abstract ▾
All authors Xin Yu, Lizhu Zhang, Jiamu Bai, Yanhong Wu, Zellux Wang, Serena Li, Weiwei Li, Lingzhou Xue, Xiangjun Fan, Bo Peng
Machine Learning
Understanding Private Evolution as Learning-Augmented Clustering
Audra McMillan, Kunal Talwar and Felix Zhou
Private
Evolution (PE) is a differentially private
algorithm for synthetic data generation. While it can be viewed as a Wasserstein learning
algorithm, it performs much better in practice than worst-case Wasserstein analyses would predict. We recast PE as generative model-augmented Wasserstein learning. We show theoretically that when we take into account the use of a generative model that is able to capture something about the true distribution, then we can obtain much better performance bounds. For example, if the generator gives samples in the same low-dimensional space as the distribution, then sample complexity depends on intrinsic, not ambient, dimension. We also show that standard variants of PE can fail to converge on simple well-clustered instances, and propose a new geometry-aware version of PE with provable convergence on such instances. Experimentally, we show that our new
algorithm is competitive with standard baselines and can improve recall.
Read the full abstract ▾
Computer Vision
ReWorld-Track: A Recursive Event World Model for Language-Guided Multi-Camera Tracking
Haoyang Wu, Shoudong Han, Chaoyue Li et al. (+3 more)
Language-guided multi-camera tracking must preserve a target identity across unobserved gaps, where similar candidates and uncertain returns can make early associations unreliable. A wrong match can corrupt the history used to predict later observations and propagate identity errors across subsequent camera handoffs. We propose ReWorld-Track, a recursive event world model that carries association uncertainty into future predictions. Candidate matches and continued waiting define alternative target states, whose posterior probabilities are used to update a persistent recurrent belief. This representation preserves uncertainty about alternative trajectories through successive observations. This belief predicts the next camera, arrival time, and entry region, while appearance and
language evidence guide association. By training across successive handoffs, the model learns to retain uncertainty that remains useful for later predictions and identity decisions. ReWorld-Track achieves HOTA scores of 65.19 on CityFlowV2 and 45.36 on MTMMC, with improved identity continuity across repeated handoffs. On MTMMC, its structured posterior update gains 0.50 HOTA points over a similarly sized generic updater and 0.94 points over fixed-moment soft association, raising next-camera accuracy from 86.03% to 87.41% and reducing median arrival-time error from 0.78 s to 0.71 s for subsequent target returns.
Read the full abstract ▾
All authors Haoyang Wu, Shoudong Han, Chaoyue Li, Sijia Chen, Zhenyang Xie, Sihan Wang