Combinatorics
Hamiltonicity of mildly pseudorandom regular graphs
Alp Müyesser
We show that if an $(n,d,\lambda)$-graph satisfies $\lambda\leq (1-\delta)d$ and $d\gg \delta^{-6}(\log n)^{3}$ for some $\delta>0$, then it is
Hamiltonian. A qualitatively similar result was recently proven by Bradač and Janzer. Our proof here is shorter and gives better quantitative bounds. \par In our proof, as in earlier work of Ferber, Han, Mao, and Vershynin, we use a random
matrix inequality to show that a mild spectral gap is typically preserved after randomly sampling an appropriate proportion of the vertices. This allows us to deduce that typical balanced bipartite subgraphs of pseudorandom graphs contain perfect matchings. To convert a collection of perfect matchings into a Hamilton cycle, we use a variant of the sorting network method.
Read the full abstract ▾
Computation and Language
Retrieving Biblical Intertextual References in Karen Blixen's Seven Gothic Tales
András Kovács, Alexander Conroy, Daniel Hershcovich et al. (+1 more)
Identifying intertextual references is central to literary scholarship, but computationally difficult when source material is transformed through paraphrase, allusion, historical
language, and translation. We investigate this problem through biblical intertextuality in Karen Blixen's Seven Gothic Tales. Drawing on the commentary to a critical edition, we construct a
benchmark of 189 annotated references and evaluate
retrieval against all 31,170 verses of historically plausible Danish Old and New Testament translations. We compare TF-IDF and BM25 with
multilingual and Danish sentence encoders, examine the effect of linguistic normalization, and fine-tune a Danish encoder using hard negatives and five-fold cross-validation. We analyze performance across automatically derived lexical-overlap strata representing quotations, paraphrases, and allusions. Linguistically normalized BM25 provides a strong zero-shot baseline, attaining an overall R@10 of 0.365 and retrieving every quotation within its ten highest-ranked verses. The best zero-shot dense model achieves a comparable overall score of 0.360 while performing better on allusions. Fine-tuning DFM-large raises its overall R@10 from 0.265 to 0.508 and more than doubles its performance on allusions, from 0.138 to 0.339. However, evaluation against editorial annotations alone understates the model's scholarly usefulness: a literary scholar judged seven of 30 selected rank-one predictions counted as false positives to be meaningful additional references. These findings show both the potential and the epistemic limits of computational intertextual
retrieval. Rather than treating scholarly annotations as exhaustive or model outputs as discoveries, we propose
retrieval models as heuristic co-readers that recover documented references and generate candidates for expert-led close reading.
Read the full abstract ▾
All authors András Kovács, Alexander Conroy, Daniel Hershcovich, Jens Bjerring-Hansen
Computer Vision
Reliability-Gated Fusion of Consumer Head and Foot IMUs for Lower-Body 3D Pose
Zhilin Guo, Boqiao Zhang, Oszkár Urbán et al. (+8 more)
Sparse inertial pose estimation promises camera-free motion capture from consumer devices, but consumer sensors are unreliable: firmware-fused orientations are biased, mounting varies between sessions, and streams drift or drop out. On a new 35-take single-subject
benchmark pairing an earbud head inertial measurement unit (IMU) with two smart-insole foot IMUs (SAM-3D-Body pseudo-ground-truth labels), we show the reliability problem is channel-level: a channel ablation isolates foot acceleration as the most informative input (66.6 mm vs. 79.0 mm head-only) and the firmware-fused foot orientation as the liability that destroys the gain. We therefore let the model learn how much to trust each channel of each stream: one temporal gate per stream per channel block, trained with an auxiliary reliability objective on synthetically corrupted pretraining data. The channel-gated model is the most accurate of our learned fusion arms on clean data (69.4 mm vs. 83.7 static, 86.6 ungated) and under every simulated fault (bias in training; drift, dropout eval-only); its gates suppress the natively biased foot-orientation channels on clean real data without test-time supervision and flag dropout bursts at 0.92-0.999 AUROC. Two contrasts: dropping a channel known a priori to fail is flat across foot faults but collapses when an unanticipated stream fails (head dropout: 92.9 vs. 79.3 mm); and a fine-tuned HMD-Poser is more accurate on clean data (64.4 mm) and nominally under drift, with no significant paired difference under bias or dropout, but a larger worst-case degradation from clean (+16.1 vs. +3.5 mm, single seed). Learning to gate reliability instead of sensor count is the lever for deployable sparse inertial capture. Code is available at https://github.com/ZhilinGuo/reliability-gated-imu-fusion.
Read the full abstract ▾
All authors Zhilin Guo, Boqiao Zhang, Oszkár Urbán, Josef Bengtson, Hakan Aktas, Wenzhao Li, Siyu Hong, Kyle Fogarty, Chenliang Zhou, Ali Senguel, Cengiz Oztireli
Machine Learning
Unifying Distributional Training for One-Step Visual Generation
Chi Zhang, Shi Haoyang, Yueyi Liu et al. (+9 more)
Distributional training provides collective supervision for one-step visual generation by matching real and generated features in frozen representation spaces. We introduce a unified theoretical framework that separates distribution modeling from matching discrepancy and connects global objectives to pointwise feature updates through Wasserstein gradient flow. Under this framework, FD-Loss and Gaussian-kernel Drifting are recovered through Gaussian optimal transport and kernel-density-based KL matching, respectively. The framework motivates MGFlow, which models feature distributions with Gaussian mixtures at an adjustable granularity between global moments and sample-based representations. MGFlow supports both optimal transport and score-based matching, and couples mass-constrained sample assignment with paired component updates to address mode collapse that mixture expressivity alone does not resolve. On ImageNet $256\times256$, MGFlow substantially surpasses the FD-Loss baseline, achieving state-of-the-art results with 1.45 $\mathrm{FDr}^6$ on pMF-H and 1.64 on JiT-H. For text-to-image generation, MGFlow post-trains FLUX.2 [klein] 4B into a one-step generator that outperforms the original four-step model on both GenEval and PickScore.
Read the full abstract ▾
All authors Chi Zhang, Shi Haoyang, Yueyi Liu, Ruichuan An, Junkang Zhou, Chang Li, Xiuyuan Lu, Yichi Zhang, Bo Wang, Yuhang Wu, Sen Cui, Miao Liu
Optimization and Control
Peppy: An AI-Assisted Workflow for Tight Convergence Analysis of Optimization Algorithms
Jaewook J. Suh, TaeHo Yoon, Edward Duc Hien Nguyen et al. (+2 more)
This paper presents Peppy, an AI-assisted workflow for discovering tight, analytic convergence proofs for first-order optimization
algorithms. Generic approaches to using LLMs to conduct mathematical research target an unspecified, broad spectrum of problems and sometimes use the Lean 4 proof assistant for formalization. On the other hand, Peppy leverages domain-specific knowledge more heavily and is thereby capable of constructing the proofs in a more structured manner, which allow a minimal and accessible verification through SymPy. We experimentally demonstrate through examples that Peppy provides a rigorous, practical, and reproducible paradigm for AI-assisted
theorem synthesis in optimization. We further highlight its capability of closing several open problems on tight convergence analysis of first-order optimization
algorithms, including
conjectures for Nesterov's FGM. Overall, Peppy is designed to turn the art of optimization
algorithm analysis into a science.
Read the full abstract ▾
All authors Jaewook J. Suh, TaeHo Yoon, Edward Duc Hien Nguyen, Bicheng Ying, Shiqian Ma
Robotics
DexRoam: Learning Mobile Bimanual Dexterous Manipulation from Egocentric Whole-Body Human Demonstrations
Rui Zhou, Yibo Yuan, Junkai Zhao et al. (+4 more)
Mobile bimanual dexterous manipulation requires continuous coordination of locomotion, whole-body motion, and finger-level dexterity within a single trajectory, creating a severe
robot demonstration bottleneck.
Egocentric human demonstrations offer a scalable alternative, but prior approaches ease the transfer by simplifying human motion, discarding exactly the fine-grained, coupled structure such tasks depend on. We present DexRoam, a complete system for learning mobile bimanual dexterous manipulation from human demonstrations, in which whole-body motion remains continuous and coupled throughout the human-to-
robot transfer process. To enable scalable collection of whole-body human manipulation demonstrations, we develop a tracker-free capture system using only a consumer VR headset and a head-mounted stereo camera, without external cameras or motion trackers. We then perform three explicit
alignment stages—embodiment, action-semantic, and temporal—to map captured motion into the
robot action space, preserving fine-grained whole-body motion and allowing human and
robot demonstrations to be jointly learned by standard VLA policies. Real-world experiments with different VLA backbones show that human demonstrations consistently improve policy learning across training paradigms, raising average success from 29% to 56% on GR00T N1.7 and from 32% to 57% on pi0.5, while matching
robot-only training with half the
robot demonstrations. Ablations confirm that each
alignment stage is necessary. These results highlight the potential of human demonstrations for scalable whole-body mobile manipulation with preserved fine-grained motion structure.
Read the full abstract ▾
All authors Rui Zhou, Yibo Yuan, Junkai Zhao, Fangyuan Zhao, Xiaoguang Zhao, Shanghang Zhang, Sirui Han
Machine Learning
TokenCast: Forecasting Token Consumption During LLM Agent Execution
Chaoqian Ouyang, Ling Yue, Libin Zheng et al. (+7 more)
When a large
language model (LLM)
agent executes the same task,
token consumption can vary by over an order of magnitude across runs. The
agent chooses its next steps based on tool feedback and intermediate results, while the growing context steadily inflates the input size of every subsequent call. The total consumption of a task is therefore hard to predict before execution and the prediction must be revised as the run unfolds. In this paper, we propose TokenCast, which learns a composable cost representation for each execution segment, recording its own consumption and the context growth it introduces. Composing adjacent segments yields a cumulative estimate that captures the extra input cost incurred when context from earlier segments is re-read by every later call. As execution unfolds, newly observed evidence refreshes the forecast, requiring no additional LLM calls and incurring a mean cumulative prediction time of 32.8 ms per run on SWE-bench Verified. Across 4 task suites and 6
agent models, TokenCast's mean absolute error reduction against the strongest comparator averages 14.5% over 96 evaluated combinations. In offline budget-control replay, TokenCast uses 21.3% fewer
tokens on average than a fixed-budget policy at matched trace completion. The code is available at https://github.com/DEFENSE-SEU/TokenCast.
Read the full abstract ▾
All authors Chaoqian Ouyang, Ling Yue, Libin Zheng, Hanghui Guo, Shengxiang Xu, YiShu Wang, Ran Li, Jian Yin, Shaowu Pan, Shimin Di
Computation and Language
Scaling Long-Form Story Generation via Narrative State Tracking
Zhennan Wan and Jianfei Chen
LLMs have demonstrated strong capabilities in creative writing. However, scaling them to full-length novels remains challenging, as maintaining narrative consistency becomes increasingly difficult. Existing story-generation methods typically focus on stories of up to about ten thousand words, leaving their ability to scale to full-length novels underexplored. In this work, we introduce Narrative State Tracking
Agent (NstAgent), a training-free agentic framework that allows LLMs to track a structured narrative state including characters, past events and future requirements. We extend an existing
benchmark to compare narrative consistency across lengths, and use it together with a writing-quality
benchmark to systematically evaluate stories ranging from 10K to 100K words. We show that NstAgent achieves better narrative consistency and writing quality as stories grow longer, and neither of them degrades noticeably as length increases, suggesting that it provides an effective approach to scaling story generation toward full-length novels.
Read the full abstract ▾
Systems and Control
Statistical Learning of Contractive Dynamical Representations for Composite Adaptive Control
Min Kim, José Leonardo Brenes, Fred Hadaegh et al. (+1 more)
We present a representation-learning framework for composite adaptive tracking control under dynamically coupled disturbances. The framework connects classical disturbance-accommodating control (DAC) to recent last-layer adaptive disturbance-rejection methods. Specifically, we introduce a statistically principled hard expectation-maximization (hard-EM) procedure, with a Kalman smoother in the hard E-step, to identify dynamical representations of disturbance whose latent
evolution is uniformly contractive. The learned representation evolves a latent disturbance-excitation state from measured plant features and control inputs and decodes that state into the time-varying disturbance acting on the nominal plant, thereby extending prior "fixed-decay" last-layer adaptive methods to a learned, predictive DAC-style formulation. Combined with
Bayesian filtering of the learned latent state, this representation yields a composite adaptive tracking controller with predictive capability and provable exponential convergence to a bounded neighborhood. We validate our approach experimentally on a slippery ground vehicle carrying a
liquid-sloshing tank and a pendulum load, and we further assess its robustness on a system of coupled Duffing oscillators. Across both settings, the method achieves accurate disturbance prediction and improved overall tracking performance relative to fixed-decay representation-learning ablations, LTI disturbance-accommodating baselines, and model-based PD baselines.
Read the full abstract ▾
All authors Min Kim, José Leonardo Brenes, Fred Hadaegh, Soon-Jo Chung
Cosmology and Nongalactic Astrophysics
Can Fingers of God be Resummed?
Shi-Fan Chen and Alejandro Aviles
Fingers of God (FoGs), Doppler shifts due to the small-scale virial motions of
galaxies, are one of the most significant challenges for analytic models of
galaxy clustering in
redshift surveys. In the effective field theory approach, the characteristic scale of these shifts introduces a new, large length scale, limiting the reach of the theory. This has motivated many phenomenological models of FoGs in the literature where their effect is approximated by a single damping function of the line-of-sight wavenumber $\lambda=k\mu$, effectively resumming powers of $\lambda$ due to single-point contractions of small-scale velocities. The goal of this work is to investigate whether such a resummation can be rigorously constructed. We show that common damping models can be understood as the mean-field limit of the single-particle characteristic function (SPCF) of FoG velocities, but that the environmental dependence of the SPCF generates equally large corrections that break the simple damping form. We develop the long-wavelength theory of the SPCF, showing that it admits an expansion in anisotropic bias operators closely related to those derived for selection effects, but with $\lambda$-dependent coefficients satisfying selection rules. We estimate these coefficients using the
halo model for DESI-like
galaxies, showing that they make significant contributions at the level of the 2- and 3-point functions of
galaxies. To answer the titular question: potentially, but at the cost of significantly expanding the operator basis and promoting free coefficients to free functions.
Read the full abstract ▾
Cosmology and Nongalactic Astrophysics
Gauge Backreaction in Standard Model Warm Inflation
Rafid H. Dejrah and Anish Ghoshal
Standard-Model warm inflation (SMWI) makes QCD the microscopic origin of inflationary dissipation, so the real-time response of the gauge
plasma enters the cosmological prediction. We show that a slowly relaxing gauge-helicity response cannot, in general, be absorbed into an effective friction coefficient and must instead remain dynamical. We therefore evolve the
quark axial densities and a matched hard-helicity mode, with QCD sphalerons and an effective $2\leftrightarrow3$ channel generating both charge transfer and correlated
stochastic sources in the full perturbation covariance system. The resulting backreaction is substantial but mainly indirect: gauge-helicity screening can reduce the warm dissipation ratio by an order-one fraction on the strong branch, while the $2\leftrightarrow3$ channel contributes only $0.2\%-0.7\%$ of the zero-density sphaleron friction directly, shifting the amplitude-normalized trajectory in both $n_s$ and $r_{\rm vac}$. The relevant trajectories, however, lack a parametrically broad hard-soft hierarchy and extend beyond strict linear response. The predictions should therefore be understood within the stated local Gaussian transport closure; a parameter-free Standard-Model (SM) result requires finite-affinity real-time $SU(3)$ drift, susceptibility, and noise kernels.
Read the full abstract ▾
High Energy Physics (Phenomenology)
Covariant Contrastive Learning for Uncertainty-Aware Anomaly Detection
Shelley Tong, Philip Harris and Gaia Grosso
Machine-learning-based anomaly detection (AD) offers a promising, model-agnostic alternative to traditional LHC analyses, allowing to search for many signals at once. Recent advances in representation learning motivate the use of neural
embeddings to map high-dimensional physics observables into low-dimensional latent spaces better suited to statistical inference. However, the propagation of systematic uncertainty in embedded spaces remains poorly understood, severely limiting the application of these methods to real LHC analyses. We address this gap with a machine learning strategy that uses a likelihood-based regularization to improve the structure of embedded spaces. Building on previous work using supervised contrastive learning for physics-aware
embeddings, our approach trains them jointly with a downstream parameterized classification task that incorporates continuous uncertainties as nuisance parameters. This method returns a latent space that covaries predictably with systematic shifts, and a model of such distortions that can be exploited in the downstream statistical test for anomaly detection. Using simulated CMS Level-1 trigger data, we show that our method successfully models continuous uncertainties in a 4D latent space with a linear parametric downstream classifier, improving both the interpretability and robustness of the statistical anomaly detection task. This framework offers a general way to study and control systematic uncertainties in latent spaces, opening the way to a new scalable statistical analysis workflow for anomaly detection at the LHC, and other high energy physics experiments.
Read the full abstract ▾
Strongly Correlated Electrons
Perfect Born Sampling of Symmetric Thermal Tensor Network States
Jianxin Gao, Qiaoyi Li, Yuan Gao et al. (+5 more)
Accurate calculations of correlated
fermions at low temperatures constitute a major challenge in
quantum many-body physics, most notably in the studies of high-$T_c$ superconductivity and ultracold atom optical
lattices.
Stochastic sampling of tensor-network states offers a promising route to tackle this problem; however, existing schemes have long faced a fundamental dilemma—sampling efficiency and
symmetry acceleration cannot be achieved simultaneously. Here we propose a perfect Born sampling approach for thermal tensor networks, which performs importance sampling directly from the purified density
matrix via the Born rule and incorporates Abelian and non-Abelian
symmetries by sampling
symmetry quantum numbers. We
benchmark the method, realized as both
stochastic matrix product states (stoMPS) and
stochastic projected entangled pair states (stoPEPS), on large-scale
quantum lattice models. Using stoMPS, we accurately simulate the square-
lattice Hubbard model on cylinders up to width $W=10$, and study the triangular-
lattice Hubbard model down to $T/t = 1/64$. We reveal scalar
chiral order at half filling and kinetic ferromagnetism upon electron doping, with the latter directly compared to ultracold atom experiments. We further extend the stoMPS method to compute finite-temperature
quantum dynamics, as demonstrated by the optical conductivity of the Hubbard model. We showcase the generalization of stoPEPS on up to $20\times20$ square-
lattice quantum Ising model, where accurate results are obtained near its
quantum critical point. Our method combines high sampling efficiency with full
symmetry acceleration. The resulting state-of-the-art framework captures both
equilibrium and dynamical properties down to ultralow temperatures, thereby providing a powerful theoretical tool for correlated
quantum systems, particularly
fermion Hubbard
quantum gas microscopy.
Read the full abstract ▾
All authors Jianxin Gao, Qiaoyi Li, Yuan Gao, Chuanshu Xu, Guoliang Wu, Su Yi, Bin-Bin Chen, Wei Li
Geophysics
AutoCF: An Automated LLM-Assisted Ecosystem for Compound Flood Simulation, Evaluation, and Impact Attribution
Soheil Radfar, Faezeh Maghsoodifar, Ning Lin et al. (+1 more)
Compound coastal flooding (CCF) arises from interacting coastal, precipitation, and river processes, yet modeling workflows often separate simulation, evaluation, and impact analysis. We present AutoCF, an automated ecosystem integrating data harmonization, model construction, observational evaluation, exposure analysis, complete factorial driver attribution, and cross-platform execution. The automated Hurricane Harvey simulation achieves a median root mean square error of 0.147 m and correlation of 0.951 across eight observational gauges, and a correlation of 0.942 with 55 high-water marks. Maximum water-level fields from CPU and GPU implementations agree within 0.01 m for 98.8% of
cells. Attribution analysis shows that during Harvey, precipitation dominated building and population exposure, whereas coastal forcing becomes increasingly important for deep and persistent inundation. The introduced Driver Impact Shift metric further quantifies whether each driver contributed disproportionately to societal consequences relative to its flooded-area contribution. Overall, AutoCF provides a reproducible pathway from CCF model construction to evaluation and driver-specific impact interpretation.
Read the full abstract ▾
All authors Soheil Radfar, Faezeh Maghsoodifar, Ning Lin, Hamed Moftakhari
Machine Learning
Neural Harmonic Measure Operator
Jinjin He, Sinan Wang, Yuchen Sun et al. (+1 more)
We introduce Neural Harmonic Measure Operator (NHMO), a neural solver for
elliptic PDE problems on variable-shape domains. The harmonic measure of a domain is the boundary probability distribution that, integrated against any boundary data, returns the Dirichlet Laplace solution. It depends only on the geometry, not on the boundary data. NHMO parameterizes the density of this measure as a
transformer-based boundary kernel supervised by Walk-on-Spheres exit samples, so one trained kernel handles different boundary values on a shape with no retraining. We extend it to Poisson via a classical decomposition, with an auxiliary network amortizing the source-induced correction and avoiding the singular volume quadrature that breaks direct evaluation. At inference, new boundary values and new sources both yield PDE solutions by re-integration against the fitted kernel and lift, with no retraining. NHMO improves over four prior baselines on the MCB-B 3D variable-shape Poisson
benchmark across all five categories, and is competitive with major neural-operator baselines on a controlled 2D testbed.
Read the full abstract ▾
All authors Jinjin He, Sinan Wang, Yuchen Sun, Bo Zhu
Machine Learning
How to Loop MoE: Flatten the Experts, Untie the Attention
Shouren Wang, Chuang Ma, Mohsen Hariri et al. (+6 more)
Looped
Transformers reuse one block of layers several times: by spending extra computation they push a model of fixed size further, and so use its parameters more fully; while sparse mixture-of-experts (MoE) models activate only a few of many experts for each
token. Looped MoE bridges these two design philosophies and gives MoE models new potential for better expert usage, but it raises a question: how to loop a MoE? We answer it with Foil. With the expert parameters and the expert compute per
token held fixed, Foil (1) flattens the experts, halving the expert layers, doubling the experts per layer and doubling the passes, so that every routing decision chooses from a larger pool, and (2) unties the
attention, giving each pass its own
attention parameters while the experts and routers stay shared. Experiments show that Foil clearly outperforms the unflattened looped baseline: at 20B
tokens every Foil model has lower pretraining loss than the baseline; at 100B
tokens the loss improves monotonically with the degree of flattening, the most flattened Foil ending 0.012 nat below the baseline at equal parameters and compute, with downstream accuracy on par or better; untying the
attention also yields more balanced and more confident routing at equal shape. Our ablations analyse why Foil works and turn the findings into design guidance for looped MoE: the returns of looping and of widening the expert layers amplify each other, routing confidence tracks healthy expert use better than load balance, and a sparse looped MoE should therefore use more experts per layer and more passes. Code and configurations are available at https://github.com/SR-A-W/how-to-loop-moe.
Read the full abstract ▾
All authors Shouren Wang, Chuang Ma, Mohsen Hariri, Debargha Ganguly, Wang Yang, Xiaoqing Tong, Qianying Liu, Xiaotian Han, Vipin Chaudhary
Machine Learning
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
Emiliano Penaloza, Dane Malenfant, Dheeraj Vattikonda et al. (+15 more)
Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU
memory. Context compaction has been the most popular mechanism to alleviate this issue, keeping GPU
memory constant for a given trace. Unfortunately, most compaction strategies rely on prefilling the LLM context many times over, hindering training throughput. To alleviate this bottleneck and enable efficient trainable compaction, we propose KV-streams, a plug-and-play strategy compatible with any compaction strategy that substantially increases throughput while showing no evidence of hindering performance. KV-streams enable scalable compaction by streaming the KV cache forward rather than flushing it after each compaction. We show that KV-streams enable three different compaction strategies, achieving a 2.6 to 5x wall-clock speedup in training. Beyond efficiency, we find that the streamed KV cache can act as a recurrent state, carrying forward information that has long since disappeared from the context. Specifically, in a controlled setting we show that, contrary to prior work, RL alone is all that is needed for this behavior to emerge. Overall, we show KV-streams to be an efficient and lightweight plug-and-play addition to any post-training pipeline.
Read the full abstract ▾
All authors Emiliano Penaloza, Dane Malenfant, Dheeraj Vattikonda, Roger Creus Castanyer, Siddarth Venkatraman, Abhay Puri, Jonathan Light, Matthew James Sargent, Augustine N. Mavor-Parker, Massimo Caccia, Lucas Caccia, Glen Berseth, Esmeralda S. Whitammer, Alessandro Sordoni, Minseon Kim, Marc-Alexandre Côté, Laurent Charlin, Guillaume Lajoie
Computation and Language
Towards Communication-Efficient Social Intelligence in Language Agents
Linxiao Gong, Yijie Xu, Tianfu Wang et al. (+7 more)
Socially intelligent
language agents must negotiate, coordinate, and resolve conflicting preferences while respecting the time and
attention of both participants. Balancing these demands is challenging because
agents must convey enough to address a partner's constraints and advance their goals without adding words that do not help the interaction. In this paper, we propose Teacher-Assisted Communication Training (TACT) to improve social goal attainment while reducing communication cost, making interactions with
agents more productive and less demanding. We first characterize communication efficiency in terms of action strategy and expression, whose effects extend beyond the current utterance to the partner's response and subsequent exchanges. We design TACT to revise student-generated actions, test the revisions through partner responses, and distill useful feedback into the student. An expression specialist removes unnecessary detail while preserving the intended action, while a strategy specialist proposes alternatives that may better address the partner's constraints. To determine which revision helps, TACT samples a partner response for each candidate and selects a teacher reference by balancing local goal support against action-
token cost. That reference guides on-policy
distillation on the student's own generation prefixes, allowing the student to act independently at deployment. We evaluate TACT on SOTOPIA and AgentSense. On SOTOPIA, it achieves the highest Goal among the evaluated methods on All and Hard while using substantially fewer target
tokens than SFT+SDPO. On AgentSense, it improves goal success over the initial student while reducing target
tokens and interaction messages.
Read the full abstract ▾
All authors Linxiao Gong, Yijie Xu, Tianfu Wang, Yin Wu, Yili Wang, Xingbo Yao, Huizai Yao, Xilin Xia, Haowen Yang, Hui Xiong
Computation and Language
Improving Test-Time Scaling with Adaptive Looped Transformers
Yichen You, Tianyu Fu, Aosong Feng et al. (+4 more)
Looped
transformers have demonstrated promising parameter efficiency by reusing layers for latent computation. Prior studies compare looped and non-looped models at matched parameters or per-
token FLOPs. However, to the best of our knowledge, whether looping improves test-time scaling as outputs grow longer remains underexplored. Through post-training looped
transformers, we study the accuracy-compute slope, measured as the accuracy gain per doubling of test-time decoding FLOPs. We find that existing looped
transformers often yield steeper slopes than their non-looped baseline, yet underperform it at matched compute. While fixed-depth looping spends extra iterations on every
token, our analysis shows that many
tokens do not benefit from extra iterations. We therefore propose TaH2, which enables the model to focus extra iterations on the
tokens that benefit from looping. It jointly post-trains the backbone and an iteration decider through lookahead depth supervision, which uses online labels indicating whether further iteration improves the prediction. TaH2 improves both the efficiency and attainable accuracy of test-time scaling. On challenging AIME
benchmarks, TaH2 improves the accuracy-compute slope by 53% (2.74 vs. 1.79) over the non-looped baseline, exceeding the baseline's peak accuracy by about 3.4 points at matched test-time compute. As the maximum iteration depth increases, existing looped models largely plateau, while TaH2's gain over the non-looped baseline continues to grow from +2.8 points at depth 2 to +3.9 points at depth 8. Our code is available at https://github.com/thu-nics/TaH.
Read the full abstract ▾
All authors Yichen You, Tianyu Fu, Aosong Feng, Xingtai Lv, Xuefei Ning, Ning Ding, Yu Wang
Earth and Planetary Astrophysics
A temperate sub-Neptune transiting the M4 Dwarf TOI-210 identified by NIRPS and TESS – Uncovering hidden M-dwarf planetary systems in the near-infrared
C. Cadieux, B. N. Skinner, F. Bouchy et al. (+63 more)
Super-Earths and sub-Neptunes dominate the
exoplanet population, yet their compositions, formation mechanisms, and capability of retaining atmospheres remain poorly understood. M-type
stars offer a unique opportunity to investigate these questions, thanks to their favorable
planet-to-
star radius and mass ratios and the diversity of planetary systems they host. We aim to characterise the planetary system of the M4
dwarf TOI-210, in which TESS during its primary mission identified one transiting
exoplanet candidate at $P= 9.01$ days. We combine multi-technique observations, including transits from 40 sectors of TESS and ground-based follow-up with LCOGT and ExTrA, and radial velocities (RV) from NIRPS obtained as part of its Guaranteed Time Observations program. These data were analysed using a
Bayesian framework to constrain
stellar, planetary, and orbital parameters. We confirm TOI-210 b, a temperate sub-Neptune ($T_{\rm eq} = 368 \pm 9$ K) with a mass of 6.75 $\pm$ 1.25 M$_{\oplus}$ and a radius of 2.234 $\pm$ 0.074 R$_{\oplus}$. Its bulk density implies a volatile-rich composition, either as an extended H/He atmosphere with mass fraction of approximately 1% (gas
dwarf), a substantial water reservoir comprising at least 29% of the mass (2$\sigma$ lower limit; water world), or a mixture of both. The NIRPS RVs show moderate evidence ($\Delta \ln Z = 5.9$) for at least one non-transiting
exoplanet interior to TOI-210 b. In a targeted search, we identify two Keplerian signals at 2.15 and 3.76 days, with minimum masses of 3.2 $\pm$ 0.8 M$_{\oplus}$ and 4.4 $\pm$ 1.0 M$_{\oplus}$, respectively, that provide a plausible explanation for the observed RV variations. If these signals are
planets, the absence of transits in the TESS photometry implies mutual inclinations with TOI-210 b above 2.3-3.5$^{\circ}$.
Read the full abstract ▾
All authors C. Cadieux, B. N. Skinner, F. Bouchy, E. D. Gillis, V. Bourrier, R. Doyon, L. Y. Messamah, B. L. Canto Martins, A. L'Heureux, Y. S. Messias, J. M. Almenara, A. K. Stefanov, X. Bonfils, K. A. Collins, H. M. Relles, C. Rodríguez, P.-A. Roy, A. Shporer, G. Srdoc, S. Taylor, C. Ziegler, R. Allart, K. Al Moulla, É. Artigau, F. Baron, S. C. C. Barros, F. Bélanger, B. Benneke, M. Bryan, T. Ciolak, R. Cloutier, N. J. Cook, N. B. Cowan, E. Cristo, L. Dang, J. R. De Medeiros, X. Delfosse, E. Delgado-Mena, X. Dumusque, D. Ehrenreich, D. O. Fontinele, T. Forveille, J. Gagné, M. J. Hobson, P. Lamontagne, I. C. Leão, R. de Lima Gomes, C. Lovis, L. Malo, C. Melo, L. Mignon, C. Mordasini, N. Nari, L. Parc, R. Rebolo, R. Rosener, J. Rowe, N. C. Santos, D. Ségransan, A. Srivastava, A. Suárez Mascareño, S. Udry, D. Valencia, G. Wade, J. P. Wardenier, D. Weisserman
Data Structures and Algorithms
Near-Optimal Bounds for Testing Residual-String Equality and Parenthesis Languages
Hadar Strauss
Residual-String Equality, denoted $\texttt{ResStringEq}$, is the property consisting of all pairs of strings over $\{0,1,*\}$ that are equal after deleting all `$*$' symbols from them. This property was first introduced by Fischer, Magniez, and Starikovskaya (SODA 2018), who used it to show a lower bound on testing the $\texttt{Dyck}$
languages, where $\texttt{Dyck}_m$ is the
language consisting of balanced sequences of parentheses over $m$ parenthesis types. They showed that testing $\texttt{ResStringEq}$ on inputs of length $n$ requires $\Omega(n^{1/5})$ queries, and presented a reduction from testing $\texttt{ResStringEq}$ to testing $\texttt{Dyck}_m$ for any $m \geq 2$. Furthermore, they showed that $\texttt{Dyck}_m$ can be tested with $O(n^{2/5+\delta})$ queries for every constant proximity parameter, where $\delta>0$ is an arbitrarily small constant. In this work, we nearly close the gap, by showing that testing $\texttt{ResStringEq}$, and hence $\texttt{Dyck}_m$ (for any $m\geq 2$), requires $\Omega(n^{2/5})$ queries. We also show a stronger lower bound of $\Omega(\sqrt{n})$ for testers that make non-adaptive queries. We establish that the $\Omega(\sqrt{n})$ bound is nearly tight, by presenting a non-adaptive tester for $\texttt{ResStringEq}$ that uses $O(n^{1/2+\delta})$ queries for an arbitrarily small constant $\delta>0$. Furthermore, we extend this non-adaptive tester to the $\texttt{Dyck}$
languages, with the same query complexity. Finally, we improve the dependence on the proximity parameter $\epsilon$ in the tester of Fischer, Magniez, and Starikovskaya, reducing it from $O(1/\epsilon)^{\mathrm{poly}(1/\delta)}$ to $O(1/\epsilon)^{O(\log(1/\delta))}$.
Read the full abstract ▾
Computer Vision
Copy the Same, Distill the Difference: Initializing Linear Vision Transformers
Huaiyuan Qin, Muli Yang, Gabriel James Goenawan et al. (+9 more)
Linear
Vision Transformers (ViTs) are designed to replace the
attention in Softmax ViTs with the linear-complexity
attention operator for more efficient
token routing, but they require from-scratch pre-training and typically underperform the original Softmax version. How to initialize linear ViTs both efficiently and effectively still remains unclear. In this work, we explicitly ask: given that most foundation ViTs are built on the mainstream Softmax
attention, can linear ViTs benefit from their pre-trained weights? Recent works on
Attention Transfer show that
attention is the effective transferable component between Softmax ViTs, suggesting
attention alone suffices for such reuse. However, we find the opposite for Softmax-to-linear transfer. The
attention weights are operator-specific: copying them barely helps, and is sometimes even worse than random initialization. Instead, the
attention's
token routing behavior can be recovered through
distillation with a proper loss design, letting linear ViTs reduce the gap and even match Softmax ones. In contrast, the MLP weights, which carry the learned representation, are operator-agnostic: they can be transferred by simple direct copying, which already carries most of the benefit of the pre-trained weights. Thus, copying MLPs can serve as an effective foundation for Softmax-to-linear transfer: paired with the distilled
attention, linear ViTs eventually close the remaining gap and even surpass Softmax ones. These findings hold consistently across various linear ViT variants, different model sizes, and diverse
datasets. We hope this study deepens the understanding of reusing pre-trained weights across
attention operators: copy what stays the same and distill what differs, to recover the benefit across the Softmax-to-linear boundary.
Read the full abstract ▾
All authors Huaiyuan Qin, Muli Yang, Gabriel James Goenawan, Shiqi Huang, Min Kass Chong, Wahyu Wiratama, Peng Hu, Chen Gong, Wu Liu, Xi Peng, Chun Jian Ho, Hongyuan Zhu
Artificial Intelligence
FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents
Hoyoung Lee, Suyeol Yun, Jack Haverty et al. (+17 more)
Evaluating finance research
agents requires rubrics that reflect expert standards and fix the values correct as of an information cutoff. Expert-reviewed finance
benchmarks rely on fixed, per-item rubrics, which are costly to extend and cannot encode each institution's own standard. In FinAutoRubric, experts specify reusable evaluation guidance, while
agents and code carry out query-specific rubric generation, review, and validation. This expert guidance governs every
agent, as
prompts and as rules that code enforces, and a Task Bank of reusable criteria carries it across tasks. In long-horizon loops that follow the expert guidance, a writer
agent researches every expected value and a reviewer
agent verifies it, and failures escalate to a human. On three expert-authored finance
benchmarks, its rubrics track expert scoring as closely as the strongest evaluated generator while stating the expert rubric's expected value for more criteria, their scores agree with human grading, and in-house analysts prefer them in a blind review. The released 100-query FinAutoRubric
Benchmark, built from in-house analysts' key questions across 78 tasks and eight asset classes, shows that rubrics from an earlier model generation still leave headroom for a later one.
Read the full abstract ▾
All authors Hoyoung Lee, Suyeol Yun, Jack Haverty, Yunju Cho, Meesong Kim, Daekyung Park, Sumin Kim, Jihoon Kwon, Jasmine Jia Geng, Andrew Chin, Yin Luo, Edward Tong, Yu Yu, Zach Golkhou, Minkyu Kim, Igor Halperin, Young Cha, Alejandro Lopez-Lira, Chanyeol Choi, Yongjae Lee
Computer Vision
InfiniHand: Streaming World-Space Hand Motion Estimation from Egocentric Video
Kerui Ren, Kaiwen Song, Weiguang Zhao et al. (+8 more)
World-space hand motion estimation from
egocentric video requires recovering 3D articulated hand geometry while tracking camera egomotion. Existing approaches heavily rely on cascading independent hand pose
estimators and SLAM systems, resulting in error accumulation, complex pipelines, and severe computational overhead. To address these limitations, we present InfiniHand, an end-to-end streaming feed-forward framework that jointly estimates MANO parameters, camera trajectories, and hand locations directly from uncalibrated
egocentric video. InfiniHand integrates persistent spatiotemporal
memory with hand-centered visual features, explicitly coupling camera motion with local hand geometry within a unified architecture. We train InfiniHand in two progressive stages by first learning robust camera-space hand priors and then extending to streaming world-space reconstruction. To support this process, we aggregate a pretraining corpus of approximately 5,000 hours of
egocentric data across multiple public
datasets. Extensive evaluations demonstrate that InfiniHand outperforms state-of-the-art baselines on in-domain
benchmarks, achieving a 21.4% reduction in ARCTIC PA-p compared to ViDiHand while substantially mitigating world-space drift. Furthermore, InfiniHand generalizes robustly to in-the-wild
videos and operates at 11.19 FPS, delivering more than twice the throughput of HaWoR.
Read the full abstract ▾
All authors Kerui Ren, Kaiwen Song, Weiguang Zhao, Yuxi Wang, Yufei Liu, Bo Dai, Haoyu Guo, Chunhua Shen, Mulin Yu, Tao Lu, Junting Dong
Networking
MINT: Modeling GenAI Impact on Network Traffic
Andrew Nguyen, Samson Kempiak, Agrim Gupta et al. (+2 more)
Generative AI (GenAI) is becoming a mainstream network workload, yet packet-level simulators lack measure\-ment-driven GenAI traffic models. Currently researchers must approximate GenAI services using traditional sources such as file transfer and
video streaming, limiting realistic network evaluation of scheduling and capacity planning. We present MINT, a measurement and modeling framework for GenAI network traffic. Using an isolated net\-work-namespace capture pipeline, we collect client-side traces from three LLM providers across four modalities, cloud and edge servers, and wired and wireless network access points. We find that GenAI modalities exhibit distinct upload/download asymmetry and burst structures that differ from traditional applications. MINT clusters and models these burst regimes and validate empirical burst timing distribution behavior in ns-3 with normalized Wasserstein distances of 2–25%. Our results also reveal that realistic packet bursts have significantly more variability than constant
token generator models. MINT open-sources the first measurement-driven GenAI traffic model for packet-level network simulation.
Read the full abstract ▾
All authors Andrew Nguyen, Samson Kempiak, Agrim Gupta, Koushik Kar, Ish Kumar Jain
Artificial Intelligence
Shockingly Simple Self-retrospection Improves Agentic Models Without RL
Jonathan Light, Christopher Zhang Cui, Jeonghye Kim et al. (+7 more)
People learn not only by repeating successful actions, but also by recounting and explaining their experiences, revising their understanding to guide future behavior. Can a
language-model
agent improve its future actions by training only on explanations of its own experience? We investigate this question by studying Retrospection-Only Fine-Tuning (ROFT), a minimal online procedure designed to isolate the effect of explanation-only training on subsequent behavior. The
agent attempts a task, observes available feedback, generates a retrospective explanation, and is fine-tuned with a next-
token prediction loss on the explanation
tokens alone. The procedure uses neither an external teacher nor a reward-based policy update. In software-engineering experiments with Qwen3.5-4B, ROFT is trained on problems with mixed successful and unsuccessful base-model attempts. On held-out SWE-bench Verified and Pro, it reaches 49.2% and 26.8% solve rates after 20 updates without using a verifier, compared with GRPO's 48.0% and 25.3% after 40 updates in the evaluated runs, and makes faster early progress in training time and sampled attempts. It also learns to solve individual tasks on which all 64 sampled base-model attempts failed, showing that learning can begin without any initially successful trajectories. Behavioral analyses find that ROFT indirectly assigns credit to actions, encouraging good actions and discouraging incorrect ones. Moreover, prompting retrospections to emphasize more direct solutions yields shorter subsequent attempts even without an explicit length penalty. Together, these findings show that learning to explain can also improve learning to do, establishing self-generated retrospections as useful training targets and motivating further study of explanation-to-action transfer.
Read the full abstract ▾
All authors Jonathan Light, Christopher Zhang Cui, Jeonghye Kim, Roger Creus Castanyer, Emiliano Penaloza, Zhengyan Shi, Alessandro Sordoni, Marc-Alexandre Côté, Xingdi Yuan, Minseon Kim
Functional Analysis
The Fourier Algebra of Certain Compact Orbit Hypergroups
Aleksa Vujičić
Let $R$ be a compact discrete valuation ring and $G = R^d \rtimes \operatorname{GL}_d(R)$. We show that the central
Fourier algebra $\operatorname{ZA}(G)$ is not amenable, reaffirming a
conjecture of Alaghmandan and Spronk. Our methods reduce to studying the
Fourier algebra of the commutative orbit hypergroup $H = R^d/\operatorname{GL}_d(R)$. Along the way, we also show that dual of any commutative orbit hypergroup $H$ is the hypergroup of the corresponding dual action, and this in turn shows that $\operatorname{A}(H) \cong \operatorname{L}^1(\widehat{H})$, which aligns with the classical setting.
Read the full abstract ▾
Information Retrieval
Rubric-Calibrated Preferences: Cross-Query Calibration of LLM Judgments via Item Response Theory
Fabian David Schmidt, Donato Crisostomi, Carlos Lassance et al. (+1 more)
Rerankers decide which documents users and LLMs see, yet their standard metric, nDCG, relies on human relevance labels that are costly, sparse, noisy, and discretely graded. As rerankers approach each other in quality, nDCG on these labels therefore increasingly fails to separate them. LLM judges could supply dense labels. Relative judgments within one query tell even close candidates apart, yet their scores share no scale across queries. Absolute grades share one scale but are too coarse to distinguish documents of similar relevance. We propose Rubric-Calibrated Preferences (RCP), which combine both kinds of judgment. A listwise Bradley-Terry tournament orders each query's documents, and a rubric of yes/no criteria of increasing stringency provides an absolute standard. Item Response Theory (IRT), which scores test-takers based on their answers to common questions, then uses the shared criteria to put all queries' tournament scores on one scale. RCP's
retrieval metric, RCP-nDCG, replaces nDCG's discrete labels with the resulting calibrated relevance probabilities. Against blind grades from 46 external annotators, calibration raises the correlation between a query's mean score and its mean human grade from 0.538 to 0.795. The probabilities rank a useful document above a non-useful one with probability 0.910 (AUC, chance 0.5), versus 0.651 for the
benchmark labels. When the annotators' grades prefer one of two rerankers and exactly one metric agrees, that metric is RCP-nDCG in 72.4% of 185 comparisons (chance about 53%). On TREC-DL, RCP-nDCG sides with NIST assessors' grades on every reranker pair that these grades separate significantly. RCP-nDCG also resolves many of nDCG's ties and separates 1.9 times as many reranker pairs on NanoBEIR. Rubric calibration thus turns relative LLM judgments into dense relevance labels that are comparable across queries and agree with human judgment.
Read the full abstract ▾
All authors Fabian David Schmidt, Donato Crisostomi, Carlos Lassance, Nils Reimers
Computation and Language
Harness Learning Enables Generalizable Test-Time Adaptation
Alvin Zhang, Xuecheng Liu, Zixuan Wang et al. (+6 more)
A
language-model
agent is jointly defined by its model and its harness, the executable program that organizes model calls, tool use, and information flow. Because different tasks call for different ways of organizing these operations, the harness needs to be adapted using feedback from the task at hand. We introduce harness learning, which trains a proposer model to revise a solver's harness using execution feedback. We formulate this process as meta-learning over executable programs, with harness revisions playing the role of weight updates in gradient-based adaptation. We train the proposer with reinforcement learning, using the task performance of revised harnesses as the reward. At test time, the proposer uses feedback from successive executions on a new task to refine the harness, without performing any parameter-space update. Experiments on
reasoning and multi-hop question answering show that harness learning improves revision quality and that the ability to adapt at test time transfers to unseen tasks. Policies trained on individual revisions can continue improving harnesses over multiple rounds, while the benefits of training on revision sequences vary across settings. These findings suggest a path towards continually learning
agents that turn accumulated experience into generalizable improvements.
Read the full abstract ▾
All authors Alvin Zhang, Xuecheng Liu, Zixuan Wang, Fahim Tajwar, Daman Arora, Ruslan Salakhutdinov, Daniel Khashabi, Yuda Song, Andrea Zanette
High Energy Physics (Phenomenology)
GAIA meets LZ: a high velocity tail-tale sign for dark matter
Anirban Das, Subhabrata Majumdar, Manibrata Sen et al. (+1 more)
The interpretation of high-energy
nuclear recoils in direct-detection experiments can depend sensitively on the high-velocity tail of the
galactic dark matter (DM) distribution. The LUX-ZEPLIN (LZ) experiment has recently reported an event, LZ230616, with
nuclear recoil energy 248 $\pm$ 23 (stat) $\pm$ 23 (sys) keV, while the
Gaia mission has provided an unprecedented view of the kinematics and mass distribution of the Milky Way. We bring these two probes together to investigate the inelastic DM interpretation of LZ230616, using a velocity distribution inferred from
Gaia-informed
galactic model. Compared to the Standard
Halo Model, the resulting distribution has a lower escape speed and a significantly suppressed high-velocity tail, with a higher local density. We find that while the exothermic interpretation is largely insensitive to this change, the endothermic interpretation requires substantially larger scattering cross sections and smaller mass splittings. Furthermore, using simulation-based study of the gravitational effects of the Large Magellanic Cloud, we show that the high-velocity tail can extend the allowed endothermic parameter space towards lower DM masses and larger splittings. Our results demonstrate how combining direct searches for DM detection with precision measurements of
galactic dynamics can qualitatively affect the particle-physics interpretation of high-energy
nuclear recoils.
Read the full abstract ▾
All authors Anirban Das, Subhabrata Majumdar, Manibrata Sen, Amogh Srivastav