Machine Learning
ResOPD: Tail Residualization for Sparse On-Policy Distillation
Penghui Yang, Long Xing, Xuanlang Dai et al. (+3 more)
On-policy
distillation (OPD) trains a student model on self-generated trajectories, but transmitting dense teacher distributions across long
reasoning traces creates prohibitive communication and
memory bottlenecks. Practical systems therefore rely on sparse teacher interfaces, typically transmitting either the sampled-
token score or a small Top-$k$ distribution. However, this sparse setting faces a fundamental dilemma: sampled-
token estimators are unbiased but suffer from severe gradient variance, whereas directly optimizing Top-$k$ objectives introduces systematic bias. To improve this trade-off, we propose ResOPD (On-Policy
Distillation with Tail Residualization), which provides unbiased full-vocabulary reverse KL gradient estimation under on-policy sampling, with substantial variance reduction under the same sparse payload in the evaluated settings. ResOPD aggregates the unobserved vocabulary into an observable coarse tail event, computes its exact aggregate gradient, and samples only the fine-grained within-tail residual, which requires no additional teacher queries or forward passes. Extensive experiments demonstrate that ResOPD substantially reduces gradient variance, stabilizes online training dynamics, and improves downstream performance across the evaluated settings. These results establish ResOPD as an efficient, plug-and-play variance reduction primitive for sparse on-policy
distillation.
Read the full abstract ▾
All authors Penghui Yang, Long Xing, Xuanlang Dai, Ziyu Liu, Kai Chen, Yuhang Zang
Performance
Energy-performance tradeoffs in server farms with batch services and setup times
Thu Le-Anh and Tuan Phung-Duc
Data centers consume a large amount of energy, much of which is wasted due to idle servers. Turning off idle servers might be an effective power-saving solution; however, there is a trade-off between energy savings and system performance. Hence, we propose a setup queueing model with a batching policy that allows servers to process a set of jobs simultaneously to minimize power consumption while maintaining acceptable performance. We consider an M/M/c/SET–BATCH queue, a multi-server batch service queue with a fixed batch size and setup times, and some variants, including systems in which idle servers delay before turning off or systems in which the batch size is dynamic. We analyze the steady-state probabilities and system performance of the M/M/c/SET–BATCH system and its variants. Our analysis of the M/M/c/SET–BATCH system with lower computational complexity is made possible by utilizing the special structure of the model. In addition, we use simulations to compare the M/M/c/SET–BATCH model with some other variants with different setup time distributions. The results suggest that the model performs better when the setup time has a larger coefficient of variation. Our results indicate that the batching policy enhances the system performance, especially when we allow servers to be idle before turning them off.
Read the full abstract ▾
Numerical Analysis
A general synthetic iterative scheme with high-order spatial discretization for rarefied gas mixture flows
Jianan Zeng and Wei Su
We develop a high-order discontinuous Galerkin formulation of the general synthetic iterative scheme (GSIS) for steady rarefied gas mixture flows. The resulting GSIS-DG discretizes the mesoscopic kinetic equations for monatomic gas mixtures and the macroscopic synthetic equations with the same
polynomial degree and solves them alternately. The kinetic solution supplies nonequilibrium corrections to the stress and heat flux, while the synthetic equations accelerate the convergence toward the steady state. Asymptotic analysis shows that GSIS-DG recovers the continuum limit without requiring the spatial mesh to resolve the molecular mean free path. Numerical results over a wide range of Knudsen numbers demonstrate high-order spatial accuracy and rapid steady-state convergence, with more than an order-of-magnitude reduction in computational cost relative to conventional kinetic iteration in the near-continuum regime. Comparisons with second-order finite-volume GSIS further demonstrate that GSIS-DG achieves comparable or better accuracy on coarser physical meshes with fewer total spatial degrees of freedom.
Read the full abstract ▾
Cryptography and Security
Bounded Reasoning: Cognitive Hierarchy in Human-versus-AI Cyber Defense
Zahra Aref, Sheng Wei and Narayan B. Mandayam
Human-
agent evaluations often compress interaction into a single performance score, even when human and automated policies adapt differently over time. We study this in a sequential cyber-defense game on an attack graph, where a human or reinforcement-learning defender protects cloud assets against a Deep Q-Network (DQN) attacker. We compare four defender settings: a human reward-only game operationalizing the DQN information structure, a human reward-plus-transition game operationalizing the Cognitive Hierarchy Theory-driven DQN (CHT-DQN) information structure, an automated DQN defender, and an automated CHT-DQN defender. In the reward-only game, participants receive payoff and reward feedback. In the reward-plus-transition game, they also see attacker-aware transition probabilities from the CHT-DQN model. Across 80 Mechanical Turk participants and matched automated simulations, human defenders adapted to outcomes in a way the automated defenders did not: they were more likely to reselect a node after a successful defense than after a failure, in both games, an asymmetry we interpret as consistent with Prospect Theory and Cumulative Prospect Theory. The 40-round average also mixes early rounds, where the DQN attacker acts mostly at random, with late rounds, where it mostly exploits; in the final stage, mean protection ranks the reward-plus-transition human game above the reward-only human game, then the automated CHT-DQN defender, then the automated DQN defender, an ordering the overall mean hides. By contrast, the reward-plus-transition game does not produce a statistically reliable overall gain in weighted data protection over the reward-only game. These results suggest that evaluating human-
agent cyber-defense systems only by an averaged task score can miss behaviorally meaningful differences in adaptation, action allocation, and bounded human
reasoning.
Read the full abstract ▾
Systems and Control
Consumer empowerment: need, definition, quantification, outcomes and challenges
Md Umar Hashmi
The transition toward decentralized digitalized and lowcarbon electricity systems is fundamentally changing the role of electricity consumers Traditionally passive endusers are increasingly expected to integrate distributed energy resources DERs and participate in energy management and demand response This paper examines consumer empowerment CE in electricity networks with a specific focus on small consumers connected to distribution networks The paper first discusses the technical economic and societal drivers underlying the growing need for CE including increasing DER penetration electrification of heating and transportation network congestion and flexibility requirements A comprehensive definition of CE is then proposed based on six elements active participation enhanced choice information and control automation and controllability selfsufficiency and resilience and energy communities with shared ownership The proposed CE definition is an explicit consideration of weakgrid where security of supply is not guaranteed To support consistent assessment across different electricity systems a framework for quantifying CE is developed based on the availability of technology and policy enablers and consumers ability to ensure security of supply The paper further reviews global experiences and implementation practices across different continents highlighting variations in technological readiness regulatory support and securityofsupply considerations Finally the expected outcomes and challenges of CE are discussed The expected outcomes of CE are improving affordability flexibility resilience
market efficiency DER integration and decarbonization while its successful implementation requires overcoming barriers related to information access digital literacy affordability regulation interoperability
privacy cybersecurity and consumer engagement
Read the full abstract ▾
Artificial Intelligence
SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
Chung-En Ho, Weiyu Sun, Cheng-Jhih Shih et al. (+3 more)
Diffusion large
language models (DLLMs) generate text through iterative block denoising, and multi-branch speculative decoding accelerates this process by verifying a main branch together with multiple draft branches in a single forward pass. While prior DLLM acceleration methods primarily exploit temporal redundancy across denoising steps, we identify a complementary redundancy axis within each speculative verification step: multi-branch computational redundancy. During speculative verification, draft branches inherit most
tokens from their parents while unmasking a small set of additional positions, causing large portions of hidden states to remain highly similar across branches. We propose SpecFold, an
algorithm-system co-design that exploits this multi-branch redundancy to reduce the cost of multi-branch speculative verification. Algorithmically, SpecFold performs
token-level residual gating and selectively reuses parent computation through folded
attention and FFN while preserving residual hidden states. Systemically, a Triton kernel implementation translates this fine-grained reuse into end-to-end throughput gains through efficient sparse multi-branch execution. SpecFold is orthogonal to temporal caching and compatible with existing DLLM speculation strategies. Across two DLLM families, five models, and five standard
benchmarks, SpecFold achieves up to 1.64x throughput over Spiffy and up to 1.99x over vanilla decoding, while maintaining comparable task performance.
Read the full abstract ▾
All authors Chung-En Ho, Weiyu Sun, Cheng-Jhih Shih, He Li, Yong Liu, Yingyan Celine Lin
Machine Learning · Cross-listed from math.PR
When the noncommutative AM-GM inequality holds
Yimin Zhong
In this note, we prove that the noncommutative AM-GM inequality holds if $n\ge 2\lceil m/2 \rceil^2$. The motivation comes from counterexamples constructed in [De Sa, Random reshuffling is not always better, NeurIPS2020]. The proof constructs a vertex measure based on the Chebyshev nodes on the Boolean cube to extract the distinct indices. The main difficulty is that the measure is not positive on non-integer nodes. The key technique comes from [Grigoriev, Complexity of Positivstellensatz proofs for the knapsack, Computational Complexity (2001)] and eventually transforms the problem into a quadrature estimate.
Read the full abstract ▾
Sound
A Multidimensional Model for Quantifying Tonal Strength: A Continuous Framework of Analyzing Tonal Evolution Beyond Tonal-Atonal Binary Classification
Yuliang Li, Nan Nan, Meilian Gu et al. (+1 more)
Tonality is a fundamental organizing principle of Western music. However, the gradual transition from common-practice tonality to atonality around the turn of the twentieth century cannot be captured by binary labels. To characterize intermediate tonal states and trace this
evolution, we propose a multidimensional framework for quantifying tonal strength, grounded in tonal theory and mechanisms underlying tonal dissolution. This framework operationalizes the global statistical regularity, temporal coherence, and local perceptual
alignment of tonal organization through three complementary features: pitch-class distribution uniformity, temporal stability of tonal centers, and local tonal clarity, respectively. To validate the model, we introduce two new
datasets: a binary
dataset comprising 196 tonal and atonal pieces, and a historical MIDI corpus of 1,561 compositions by 21 composers spanning the Baroque era to the early twentieth century. The proposed model achieves high discriminative performance on the binary classification task (F_1=0.985), and quantitatively reveals a continuous historical trajectory from established tonality through progressive weakening to eventual dissolution. Computational analysis of representative composers further confirms significant declines in tonal strength throughout the careers of late-Romantic and modernist figures. Additionally, analysis of EMOPIA
dataset reveals a weak but statistically significant positive correlation between higher tonal strength values and positive emotional valence. This work establishes a unified quantitative model for analyzing tonal
evolution and provides a continuous measure for future behavioral and neurophysiological investigations of the relationships among tonal organization, musical
emotion, and cognition.
Read the full abstract ▾
All authors Yuliang Li, Nan Nan, Meilian Gu, Xiaohong Guan
Machine Learning
Your Temporal Link Predictor Is Blind to Who Is Active: A Missing Factor That Transfers Across Models
Ji Zhang, Zixin Liu, Yiran Ding et al. (+3 more)
An interaction has two parts: someone decides to act, and then chooses whom to act on. Temporal link prediction has concentrated on the second, and we show that it is blind to the first by construction: a standard negative keeps the real source and swaps the destination, and we prove that this cancels the source's activity exactly from the optimal score, so no model trained and evaluated this way is ever rewarded for learning it. Under the harder historical and inductive negatives, whose sources differ, the same factor becomes the dominant signal. We model it with Source Node Activity Modeling (SNAM), a self-exciting event intensity fitted by an exact point-process likelihood to decayed interaction counts the history states already contain; it has fewer than 20 parameters. On their own, never looking at the destination, these parameters beat DyGFormer and TPNet on four of five
datasets under historical negatives. Added to the frozen scores of TPNet, TGN, DyGFormer and DSRD, four models of different design, without retraining anything, they raise AP on almost every backbone-
dataset pair in both settings, by up to 25 points. Our full model ranks first overall against eleven baselines on 13
datasets and three protocols, and on million-event streams trains an epoch 9-100x faster than TPNet and DyGFormer. We conclude that source activity is a blind spot of temporal link prediction, and a cheap, transferable one to close. Code is available at https://github.com/Erutaner/Your-Temporal-Link-Predictor-Is-Blind-to-Who-Is-Active.
Read the full abstract ▾
All authors Ji Zhang, Zixin Liu, Yiran Ding, Jiayi Wang, Yilu Du, Weijia Xuan
Artificial Intelligence
From Memory to Guide: Spatio-Temporal Composer for Procedural Coding Memory
Zhixuan Tan, Pengjie Gu, Zhao Li et al. (+4 more)
Memory-augmented
agents typically integrate procedural knowledge by injecting retrieved skills directly into text
prompts. This approach dangerously equates readable text with reliable execution. To bridge this gap, we introduce From
Memory to Guide, a novel paradigm that transitions procedural
memory from passive text delivery to active, inference-time policy adaptation. We instantiate this paradigm through the Spatio-Temporal Composer, an active policy compiler that explicitly manages exactly how and when retrieved knowledge should be applied. Rather than treating skills as plug-and-play modules, Composer dynamically aligns historical knowledge with current environmental constraints (spatial adaptation) and precisely dictates its applicable lifecycle (temporal orchestration). It actively transforms static
memories into strictly bounded Runtime Guides—equipping the
agent with localized objectives and behavioral guardrails without requiring a single parameter update. Extensive evaluations on 13 demanding, long-horizon software engineering tasks in EngramBench demonstrate the clear advantages of this architecture. Composer not only robustly prevents context mismatch but drives an absolute pass-rate increase of 7.2 percentage points on the most complex tasks, while simultaneously slashing the main
agent's
token usage by 32.2%.
Read the full abstract ▾
All authors Zhixuan Tan, Pengjie Gu, Zhao Li, Yihan Hu, Xu He, Dong Li, Jianye Hao
Machine Learning
Greedy Local Learning for Language Model Pretraining: Gaps and Objective Design
Jihwan Moon, Sheir A. Zaheer, Jinmyoung Lee et al. (+2 more)
Greedy block-wise local learning splits a network into gradient-isolated blocks trained by local auxiliary losses, deleting the backward pass between blocks: inter-stage communication becomes forward-only and every block can step its optimizer independently, properties directly relevant to decentralized model-parallel training. Local learning is competitive with end-to-end backpropagation on image classification, and on small
Transformers it is known to trade a worse best loss for parallel speedup. How this loss gap behaves in autoregressive
language model (LM) pretraining at larger scale, and which auxiliary designs reduce it, has not been measured. We present a
token-budget-matched empirical study at 125M and 400M parameters with $K \in \{1,2,4\}$ blocks at Chinchilla-optimal budgets, factorizing the auxiliary design into network architecture and training objective. We observe: (i) the gap to end-to-end training more than doubles from $K=2$ to $K=4$, but at $K=4$ shrinks from 125M to 400M; (ii) replacing an MLP auxiliary with a
Transformer-based one is a strong network-side intervention, recovering 22-41% of the gap; (iii) a multi-
token-prediction (MTP) auxiliary objective helps at the first block boundary, whereas adding it at deeper boundaries hurts, and restricting it to the first block yields the best $K=4$ configuration ($+0.062$ vs. $+0.075$ nats at 400M); and (iv) deployment-style per-block execution reduces activation
memory by up to $2.2\times$. We frame these results as an empirically grounded method direction rather than a finalized method: local objectives should apply future-predictive pressure selectively across boundaries while resisting shortcuts that bypass predictive content.
Read the full abstract ▾
All authors Jihwan Moon, Sheir A. Zaheer, Jinmyoung Lee, Gunhee Kim, Chan Y. Park
Computer Vision
Enhancing Long-Video VLM Embeddings with Query-Aware Streaming Latent Reasoning
Haozhe Chi, Song Jin, Yang Jin et al. (+1 more)
Long-
video embedding requires capturing sparse query-relevant evidence under a limited visual-
token budget. Uniform sampling can miss brief events in
videos spanning minutes or hours, whereas encoding more frames in a single context increases
memory and computation. We introduce Query-Aware Streaming Latent
Reasoning (QASLR), a post-training framework that accumulates evidence across clips while keeping the
embedding size fixed. QASLR selects a bounded set of frames, restores their temporal order, and processes them clip by clip with a
vision-
language backbone. A compact set of persistent think
tokens cross-attends to each clip's features, while an embed
token reads out a normalized representation after every update. This design integrates evidence across multiple backbone calls without requiring all selected frames to share a single context. Training combines final contrastive learning, step-wise contrastive supervision, and final-
embedding self-
distillation. Intermediate supervision trains partial-
video readouts for
retrieval, while self-
distillation regularizes them toward the final representation. Query-aware selection produces query-conditioned representations for candidate-set scoring and reranking, whereas query-independent selection enables reusable corpus indexing. Under the full training recipe, HourVideo
retrieval Hit@1 increases from 54.2 to 70.7 and from 57.4 to 72.8 for 2B and 8B Qwen3-VL-
Embedding backbones, respectively. Gains extend to the evaluated moment-
retrieval and
video-QA tasks, and the streaming head transfers to a second Qwen-family
embedding backbone. These results support streaming latent aggregation as an effective approach to integrating long-
video evidence into fixed-dimensional representations.
Read the full abstract ▾
All authors Haozhe Chi, Song Jin, Yang Jin, Yadong Mu
Artificial Intelligence
GitSwarm: Decentralized Compounding Inference
Vedant Shah, Ankur Samanta, Paras Dahal et al. (+11 more)
Long-horizon problem solving and scientific research require computation to accumulate across successive attempts. Partial solutions, experimental findings, and unsuccessful approaches can inform later work, yet most inference-time computation is organized around individual trajectories or candidates rather than a persistent body of reusable work. We call this paradigm compounding inference: organizing inference-time computation so that intermediate work persists and can be inspected, extended, combined, or challenged by subsequent computation. We instantiate compounding inference in GitSwarm, an asynchronous system where homogeneous
agents independently decide how to advance a task while collaborating through structured persistent
memory.
Agents explore, experiment, verify, refine, and synthesize previous work in a shared, branch-able Git repository. Atomic commits preserve intermediate artifacts, while explicit semantic dependencies record how later contributions build on work across branches. We evaluate GitSwarm on long-horizon problem solving and sustained GPU-backed experimental research. On IMOProofBench-Advanced, GitSwarm solves all 30 problems in one run using GPT-5.5. On ProgramBench, it achieves a $79.4\%$ mean score, versus $65.1\%$ for the strongest reported baseline under the stated budget. On three neural architecture research tasks (Residual
Matrix Transformer, Looped
Transformer, NanoChat), GitSwarm improves upon the starting architectures through successive experimentation. Beyond final performance, we measure whether computation accumulates: on ProgramBench, $94.7\%$ of contributions are subsequently built upon, while the selected solution's ancestry covers $82-93\%$ of the contribution graph. These results show that inference-time computation can accumulate across otherwise independent episodes, forming an evolving body of work that subsequent inference can reuse.
Read the full abstract ▾
All authors Vedant Shah, Ankur Samanta, Paras Dahal, Mikhail Plekhanov, Carole-Jean Wu, Scott Yih, Remi Munos, Rob Fergus, Jakob Foerster, Ruslan Salakhutdinov, Sanjeev Arora, Jason Weston, Aaron Courville, Anirudh Goyal
Operating Systems
Awkernel: RTOS Bridging DAG Scheduling Theory and Component-Oriented Real-Time Systems Practice
Atsushi Yano, Ryo Nishimura, Yutaro Kobayashi et al. (+3 more)
Real-time directed acyclic graph (DAG) scheduling provides a rigorous basis for timing analysis and efficiency in component-oriented real-time systems (CORTS) such as autonomous driving systems, yet challenges remain from the perspectives of both theorists and practitioners. For theorists, no OS natively supports the DAG task model;
algorithms are therefore evaluated only analytically or in simulation, ignoring real-hardware overheads. For practitioners, today's CORTS platforms (ROS~2 and AUTOSAR Adaptive Platform) are designed for service composition rather than timing analyzability; adopting DAG scheduling research therefore demands substantial code changes and developer discipline. This paper proposes Awkernel, the first open-source real-time operating system (RTOS) that natively supports real-time DAG scheduling research, bridging DAG scheduling theory and CORTS practice. For theorists, Awkernel is a real-hardware testbed: it exposes a modular OS-native DAG scheduler for easy
algorithm implementation, plus a random workload generator and built-in metrics for evaluation. For practitioners, Awkernel is not a full replacement for today's platforms but a CORTS platform maximizing timing analyzability: its familiar publish/subscribe model keeps porting mechanical, mapping each callback to one subtask. Moreover, its function-as-subtask (FasS) API enforces DAG semantics (precedence constraints) without programmer discipline, yielding applications that match the theoretical DAG model and directly inherit its efficiency and safety guarantees. On a Raspberry Pi~4, microbenchmarks confirm microsecond-level scheduling overheads; a global earliest deadline first (GEDF) scheduler fits in 226~lines; and a practitioner ports part of an autonomous driving system using only the FasS API, without
reasoning about DAG semantics.
Read the full abstract ▾
All authors Atsushi Yano, Ryo Nishimura, Yutaro Kobayashi, Yuuki Takano, Takahiro Ishikawa-Aso, Takuya Azumi
Cryptography and Security
Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
Haocheng Ye, Aoting Hu, Xinwei Zhang et al. (+3 more)
Text watermarking helps identify AI-generated content, but its effect on factual reliability remains underexplored. In this paper, we study watermarking
hallucination: factual errors induced or amplified by watermarking even when the required evidence is present in the context and the unwatermarked model can answer correctly. Using a controlled
retrieval-augmented generation setting, we compare unwatermarked and watermarked generations under the same context, query, and decoding configuration, and quantify their factual accuracy decrease. Across six representative watermarking methods, including KGW, SWEET, DiPmark, GumbelSoft, Gumbel-Max, and SynthID watermarking, we consistently observe watermark-induced
hallucination. Watermarked outputs can remain fluent while introducing factual errors. We attribute this failure mode to two mechanisms: (1)
token perturbations in the current-step arising from method-specific reweighting or keyed sampling, and (2) prefix-induced
attention drift, which accumulates through autoregressive decoding and weakens later
attention to the factual context. Motivated by this analysis, we propose two plug-in interventions at the
token and
attention levels that can be integrated into existing watermarking methods to improve factuality. At a matched TPR of 0.90 at 1% FPR, combining the two interventions reduces factual errors by approximately 90% relative to watermark-only decoding while preserving fluency and comparable decoding efficiency. Overall, this work highlights factuality as a first-class criterion in watermark evaluation, alongside detectability and robustness, and calls for careful factuality validation before deploying watermarks in fact-critical applications.
Read the full abstract ▾
All authors Haocheng Ye, Aoting Hu, Xinwei Zhang, Xunzhu Tang, Shuchao Pang, Jason Xue
Systems and Control · Cross-listed from math.OC
Communication-Efficient Differentially Private Gradient Tracking for Distributed Optimization via Local Updates
Mihitha Maithripala, Chenyang Qiu and Zongli Lin
This paper studies
privacy-preserving distributed optimization using gradient tracking with one communication-free local update between consecutive communication rounds. Since local computation alone does not protect gradient information, we perturb both the primal state and the gradient-tracking direction at communication iterations while keeping local updates noise-free. We establish an aggregate variable for tracking, characterize the limiting consensus point in the presence of added random noise, and prove convergence in mean under certain parameter conditions. We also establish infinite-horizon pure differential
privacy for the complete communication transcript under an affine objective adjacency relation and geometrically decaying Laplace perturbations. Simulation results illustrate the advantages of the proposed method in terms of the convergence and optimization accuracy given a
privacy budget.
Read the full abstract ▾
Computer Vision
One Tile, Multiple Instances: Rethinking MIL for Sparse Diagnostic Evidence
Runsheng Liu, Cheng Jin, Hao Jiang et al. (+1 more)
In weakly supervised Whole Slide Image (WSI) classification, feature extractors typically compress each image tile into a single global
embedding. Consequently, slide-level aggregators are restricted to this coarse tile scale, concealing fine-grained sub-tile evidence from the
attention mechanism. We introduce DI-MIL, a framework that decouples encoding context from instance granularity through decomposed instances. By clustering dense spatial
tokens from a frozen foundation model within each tile, DI-MIL converts a single tile into multiple independently weighted instance
embeddings. As a training-free post-encoding module, DI-MIL integrates seamlessly into existing pipelines without requiring re-encoding or downstream architectural modifications. We evaluate DI-MIL on cytopathology, a challenging testbed where sparse diagnostic signals are easily diluted within standard tiles. Across four
datasets, three frozen foundation models, and two
attention-based aggregators, DI-MIL demonstrates consistent efficacy, improving 67 of 72 metric-level comparisons, with the largest mean gains reaching 3.64 points under cytopathology-specific backbones. In a broader comparison against seven representative MIL baselines, DI-MIL paired with ACMIL achieves highest mean performance in 33 of 36 backbone-
dataset-metric comparisons. Ablations show that direct smaller tiling inflates the extracted tile count by up to 43.3$\times$ with non-monotonic performance, whereas DI-MIL incurs zero additional image-extraction overhead while achieving the strongest overall results. These results establish instance construction as an orthogonal design dimension in MIL, supporting DI-MIL as a cost-efficient solution under sparse diagnostic evidence.
Read the full abstract ▾
All authors Runsheng Liu, Cheng Jin, Hao Jiang, Hao Chen
Networking
Hybrid Ray-Tracing and Physics-Embedded Neural Modeling for High-Fidelity Channel Reconstruction in Wireless Digital Twins
Huiwen Zhang, Chu Ma and Feng Ye
Many existing wireless digital twins (DTs) rely heavily on ray-tracing (RT)-based channel simulators to achieve scalability in large-scale environments. However, the
geometric-optics (GO) approximations underlying RT become inaccurate in propagation regimes dominated by diffraction and refraction, which are prevalent at sub-6 GHz carrier frequencies. This paper presents a hybrid RT and physics-embedded physics-informed neural network (PE-PINN) framework that enhances site-specific wireless DTs with physics-consistent full-wave accuracy. Building on prior PE-PINN work, we introduce targeted architectural extensions, including a finite-length edge diffraction kernel and a lossy dielectric formulation based on complex wavenumbers, to accurately model electromagnetic wave interactions with realistic objects and materials. To balance accuracy and efficiency, we further propose a localized tunnel strategy that deploys PE-PINN models only along dominant propagation paths, selectively replacing or augmenting RT predictions in regions where GO assumptions break down. Comprehensive evaluations against full-wave COMSOL simulations demonstrate that the proposed framework closely matches reference solutions and significantly outperforms RT-only approaches in diffraction- and refraction-dominated scenarios. We further demonstrate seamless integration of the proposed approach into a realistic indoor wireless DT, highlighting its practicality and scalability for next-generation wireless network design.
Read the full abstract ▾
Machine Learning
CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery
Tao Feng, Fangxu Yu, Zijie Lei et al. (+5 more)
Open-ended discovery requires learning from repeated attempts while continuing to explore directions whose value is not yet apparent. Search with a frozen large
language model (LLM) can reuse previous solutions in context, but cannot update the model from its successes and failures on the test problem. Reinforcement learning (RL) enables such adaptation; however, strongly favoring high-reward trajectories may suppress low-reward yet potentially promising directions too early. We introduce CURIO, a curiosity-driven test-time learning framework that complements task feedback with an Intrinsic Curiosity World Model (ICWM). The ICWM learns transitions in the policy's hidden-state representation and supplies prediction-error bonuses at sampled
tokens outside the policy's top-k choices. Epoch normalization and an annealed weight regulate their contribution to the policy update. On six mathematical discovery tasks and single-
cell denoising with Qwen3 backbones from 8B to 235B, three-run means improve over a matched task-only RL control on five mathematical objectives, match the best reported performance on Circle Packing, and improve denoising Score and mean squared error (MSE) on both held-out corpora at every tested scale. Relative gains reach 18.3% on Hadamard and 10.8% on denoising Score. Code-diversity measurements show greater structural variation among generated programs, supporting curiosity as a complementary exploration signal for learning in open-ended discovery.
Read the full abstract ▾
All authors Tao Feng, Fangxu Yu, Zijie Lei, Jiaru Zou, Changjiang Jiang, Yi Yan, Jiaxuan You, Pan Lu
Machine Learning
PIT-GCL: Protein Interaction using Topological Graph Contrastive Learning
Jae Won Choi, Ryoonki Hong, Alan Liang et al. (+5 more)
Protein binding prediction is central to target identification, therapeutic binder design, and large scale screening, yet remains challenging because binding depends on sequence, three dimensional geometry, and global structural organization. Recent folding models such as AlphaFold3 and Boltz-2 have substantially improved structure prediction, but their confidence outputs (pLDDT, pTM, ipTM) are not specifically designed for binary binding prediction, and dedicated structure aware predictors often require bound complex structures that are unavailable at screening scale. We introduce PIT-GCL, a dual tower structure aware framework that encodes each
protein independently from its amino acid sequence, C{\alpha} point cloud, and a global persistent homology descriptor. Each tower combines residue ESM-2
embeddings with a topological summary computed from the H0 and H1 persistence landscapes of a Vietoris-Rips filtration, and processes the resulting
tokens with a structure aware
Transformer in which pairwise C{\alpha} distances enter as a learned
attention bias. A bidirectional cross
attention module then performs latent space soft docking between the two per-
protein representations, and the model is trained with a combined binary cross
entropy and NT-Xent contrastive objective. On three binary interaction prediction
benchmarks, general PPI on PPIRef, TCRpMHC binding on STAG, and whole chain pairs on PPB-Affinity, PIT-GCL outperforms representative sequence based, structure aware, and task specific baselines on general PPI under our evaluation, and is the only method above chance on PPB-Affinity; on TCR-pMHC it leads at a fixed decision threshold but is outranked by a task specific sequence model. Because each
protein is encoded independently in the first phase, its representation can be precomputed and reused across candidate pairs, which is convenient for large scale screening.
Read the full abstract ▾
All authors Jae Won Choi, Ryoonki Hong, Alan Liang, Manjula Adiveppa Wader, Bingsong Zeng, Peiyang Tang, Longwei Liu, Ruishan Liu
Machine Learning
Which Preferences to Train On? End-to-End Multi-Objective Alignment with an Adversarial Preference Distribution
Minjae Lee, Kyunghyun Cho and Sangdon Park
Aligning large
language models (LLMs) with human values is important for safe, efficient, and beneficial AI deployment. However, human values are multifaceted: helpfulness, harmlessness and humor trade off against one another, and different users want different trade-offs. Multi-objective
alignment (MOA) addresses this by training a policy that can provide any point of the Pareto front, but existing methods either train one model per preference, interpolate a few separately aligned experts post hoc, or train a single conditioned model without considering which preferences it should be trained on. Since the hard regions of the preference simplex depend on the objectives at hand, existing methods leave them under-trained and do not get the most out of a single model. Therefore, we propose MAESTRO (Multi-objective
Alignment via End-to-end STeering and Robust Optimization), which formulates MOA as a minimax problem over preference distributions and trains a single
prompt-conditioned policy end-to-end with RL against an
adversarial preference distribution: a Dirichlet distribution updated by online mirror descent toward the preferences the current policy serves worst, rather than on a fixed one. On HH-RLHF, BeaverTails and a summarization task, with up to three objectives, MAESTRO attains the best Pareto front on most tasks in a single training run, at the lowest training cost among the compared methods. The largest margins appear in the hard regions that a fixed preference distribution leaves under-trained, confirming that a single
prompt-conditioned model is capable of covering the objective trade-offs on its own.
Read the full abstract ▾
Formal Languages and Automata · Cross-listed from math.NT
Proofs of some OEIS conjectures on Wythoff sums, Fibonacci and Lucas words
Alex Ashburn
We prove several
conjectures from the On-Line Encyclopedia of Integer Sequences about the lower and upper Wythoff sequences and the Fibonacci word. Among them are two of Kimberling's three
conjectures on the number of ways to write $n=\lfloor h\varphi\rfloor+\lfloor k\varphi^2\rfloor$ with $h,k\ge1$ (A259598): exactly one way if and only if $n+1=2F$ for a Fibonacci number $F\ge2$, and exactly two ways if and only if $n+1\ge7$ is a Lucas number. The third
conjecture, that no way exists if and only if $n+1$ is a Fibonacci number, was proved earlier by Kawsumarng et al. We also observe that Kimberling's
conjecture on the gaps of the sums of two distinct terms of A003622 and of their complement (A333308, A333309) follows, after a shift by $2$, from earlier Walnut results of Shallit and of Bosma et al. on A260317, and we re-verify it. Next, we prove Kimberling's five 2025
conjectures on the gaps between positions where the Fibonacci word and the "Lucas word" take prescribed values (A383423-A383427). Finally, we prove a
conjecture of Mathar on A285383, and we point out that a
conjecture of Schmidt on A003250 follows from
theorems of Carlitz, Scoville and Vaughan (1973); we also confirm it with Walnut. Most proofs are decision procedures run in the free prover Walnut, and we supply the complete command file.
Read the full abstract ▾
Computational Engineering
PuriGen: Purity-Aware Deep Generative Modeling for Predicting Stem Cell Lineage Fate
Yanli Li, Tianying Sheng, Hala Zreiqat et al. (+2 more)
Predicting stem-
cell lineage fate is central to elucidating biomaterial-stem
cell interactions and optimizing strategies for tissue regeneration. While existing approaches demonstrate the feasibility of lineage prediction, they remain limited in modelling compositional heterogeneity and time-dependent differentiation dynamics. To mitigate this gap, we propose PuriGen, a purity-aware deep generative framework for biomaterial-induced lineage prediction from bulk transcriptomic data. PuriGen consists of two key modules, PuritySCVI and PuritySCANVI, which extend scVI and scANVI by incorporating a pretrained GBMPurity head to provide a sample-level purity-like compositional signal. In addition, purity-aware regularisation and temporal constraints are introduced to encourage informative purity prediction and biologically consistent latent representations. Experiments on bulk mesenchymal stem-
cell datasets collected across multiple biomaterial conditions and induction stages show that the proposed framework achieves better performance than the existing methods.
Read the full abstract ▾
All authors Yanli Li, Tianying Sheng, Hala Zreiqat, ZuFu Lu, Zhiyong Wang
Artificial Intelligence
MemTrace: State-Consistent Memory for Long-Horizon Coding Agents
Hongming Xu, Le Zhou, ZhongHe Jin et al. (+5 more)
As coding
agents take on long-horizon software
evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupled challenges: (1) accumulated histories strain context budgets, and (2) repository changes can invalidate earlier execution evidence. Existing approaches address these challenges through techniques like larger context windows, compression,
retrieval, or repository representations, but often fail to reconstruct a consistent task state after a context refresh or verify whether recalled evidence remains valid. Thus, we introduce MemTrace, a provenance-aware
memory system that preserves execution history and aligns its reuse with the evolving task (e.g., iterative cross-file repair) and repository state. MemTrace stores history as immutable
Memory Traces anchored to key information (e.g., files, symbols, tests), and organizes their execution order and dependencies in a
Memory Trace Graph. When context is constrained, working
memory retains only compact
Memory Anchors, from which the
agent can reconstruct the latest execution state and locate evidence relevant to its next action. Before restoring historical evidence, MemTrace checks its validity against the current repository state and retrieves only what the next action requires. Across three complementary long-horizon coding
benchmarks, MemTrace consistently outperforms all fully evaluated baselines under the same backbone and harness, improving DeepSWE pass@1 by 21.2 points, SWE-EVO Resolved Rate by 4.4 points, and SWE-Milestone Score by 17.8 points under Codex CLI.
Read the full abstract ▾
All authors Hongming Xu, Le Zhou, ZhongHe Jin, Xiang Zhang, Bo Tang, Zhiyu Li, Xuanhe Zhou, Juncheng Zhang
Software Engineering
CARET: Training-Free Test-Time Scaling for Repository-Level Code Completion
Jiajie Wang, Yutong Zhao, Kebin Peng et al. (+3 more)
Retrieval-augmented generation (RAG) dominates repository-level code completion: it retrieves cross-file context (R), then decodes one greedy completion (G). Existing work mainly focuses on
retrieval and stops there. We argue both stages can be improved together, with generation in particular gaining from test-time scaling. We present CARET, a training-free method. For R, CARET routes among
retrieval contexts using the agreement among its own samples, cascading to an alternative context when the samples scatter. For G, it samples candidates over a cached
prompt prefix, so the long retrieved context is encoded once rather than once per sample. It then selects the final completion by reverse-context likelihood: a correct completion makes the code after the cursor more probable, so the same model grades its own candidates by reading ahead. Across CrossCodeEval, RepoEval-Line, and RepoEval-API with six code models (1.1B to 7B, four families), CARET improves exact match in all 18 combinations by 10.8 points on average over greedy decoding and 5.3 over self-consistency@10.
Token-level compute stays near 1.45 times one generation (measured wall-clock 1.3-2.9 times, growing with generator size). Improving
retrieval and generation together yields more accurate code than improving
retrieval alone, at a budget that stays close to a single pass.
Read the full abstract ▾
All authors Jiajie Wang, Yutong Zhao, Kebin Peng, Sen He, Qing Guo, Tianlin Li
Computer Vision
RSure-Agent: Reliable Use of Tool Observations for Remote Sensing Agents
Fuyuan Liu, Nayu Liu, Wenhao Yu et al. (+5 more)
Remote sensing
agents rely on perception, measurement, and raster analysis tools to solve Earth observation tasks. We refer to their judgments and quantitative results about ground objects as tool observations. However, these observations are subject to substantial uncertainty and may be incorrect even when the tools execute successfully. When
agents accept incorrect observations, the errors can propagate through subsequent
reasoning and cause task failure. We analyze 1,229 execution trajectories across three remote sensing
agent benchmarks. On each
benchmark, at least 88.1% of tasks depend on tool observations. Among these tasks, at least 22.7% contain incorrect observations despite successful tool execution. These errors propagate to the final answer in at least 82.0% of affected tasks on each
benchmark. To address this problem, we propose RSure-
Agent, a framework for verifying tool observations and limiting error propagation. We introduce a verifiable observation protocol that requires tools to return process evidence for the
agent to verify their observations. We also construct a task-tool reliability prior from offline task feedback. The prior summarizes each tool configuration's past performance across task types and provides a task-specific reference for verification. Using process evidence and this prior, RSure-
Agent decides whether to accept an observation, request additional evidence, or reject it. We evaluate RSure-
Agent on EarthBench, ThinkGeo, TerraLogic, and CHOICE-420. Across the three
agent benchmarks, RSure-
Agent reduces the error propagation rate by 21.3 to 25.9 percentage points relative to the base configuration with verification and the prior disabled. On CHOICE-420, it improves overall accuracy over direct answering by 5.71 percentage points on average across 11 backbone models. On EarthBench, it reduces the tool-call ratio by 25.9% relative to Earth-
Agent.
Read the full abstract ▾
All authors Fuyuan Liu, Nayu Liu, Wenhao Yu, Peijin Wang, Yingchao Feng, Fanglong Yao, Liang Wan, Wei Feng
Information Theory · Cross-listed from quant-ph
Quantum codes in the Lee metric
Jinkang Guo, Yiqiu Han, Aranya Chakraborty et al. (+4 more)
We introduce a
quantum coding framework for discrete small-shift noise, in which errors on qudits are modeled as low-weight $X$- and $Z$-type Pauli shifts, analogous to small phase-space displacements in continuous-variable systems. This structure is approximately respected by
nuclear-
spin noise and captured by the Lee metric, motivating a
quantum extension of classical Lee-metric coding theory. We develop such a formalism for stabilizer codes over $\mathbb{Z}_q$ for arbitrary $q$, using joint and separate Lee metrics for the $X$- and $Z$-components of errors. For
qubits, the joint metric counts $Y$ errors twice and can yield codes that detect and correct $X$ and $Z$ errors with fewer physical
qubits than codes designed for the conventional Hamming metric. We discuss Lee-weight spreading under Clifford gates and qubitize codes over $\mathbb{Z}_4$ via the Gray map, finding codes with two-fold transversal non-
qubit-Clifford gates. For
quantum CSS Lee-LDPC codes on $n$ qudits, we prove that the Lee distance cannot exceed $O(n)$, uniformly in $q$, demonstrating an unexpected obstruction to using the large internal
Hilbert space of a large-$q$ qudit to make high-Lee-distance codes. Under local Metropolis dynamics, certain classical $q$-ary “helical repetition codes” have exponentially long
memory times at fixed temperature for sufficiently large $q$ (that grows with system length), which can be understood as spontaneous
symmetry breaking at finite temperature, even in local one-dimensional models. Hypergraph products of these helical repetition codes provide local two-dimensional
quantum codes that inherit self-correction for $Z$ errors, but self-correction for $X$ errors remains an open question.
Read the full abstract ▾
All authors Jinkang Guo, Yiqiu Han, Aranya Chakraborty, Shubham P. Jain, Tianhao Liu, Victor V. Albert, Andrew Lucas
Software Engineering
Jiajie Wang, Yutong Zhao, Tianlin Li et al. (+4 more)
Agent Skills, the SKILL.md files that tell an LLM coding
agent how a project works, are revised like code, yet what a revision does to the
agent is unknown. From 2,608 first/last revision pairs of 3,159 Skills, we characterize how Skills evolve and how they change together with the configuration of the
agent's harness. We then focus on rule changes, revisions that add or remove a rule we can check automatically, such as "run allium check". We measure their effect on 21 models in single answers and on four
agents in a sandbox, and their cost on 20 of these models and the four
agents. Most revisions (55%) change a rule or procedure, and commits that revise a Skill change harness files such as CLAUDE.md more often than other commits of the same size. Across 16 open-weight models, an added rule raises compliance in a single answer by +0.41 on average. Across the four
agents, the rate at which the
agent takes the required action rises by +0.23 on average (+0.16 to +0.36), and for the three
agents that blind judges assessed, final correctness rises by +0.10 on average (+0.06 to +0.14). The gain comes mainly from rules that name a command or path the old Skill did not mention. Real tools load a Skill's body only when the
agent decides it needs it. In that setting the four
agents keep about half of the action gain on average (51%), and the three open models about 38%. A revision adds 18-19% input
tokens to a single answer and no detectable cost to an
agent episode, while loading a Skill's body raises the
tokens of an episode by 50% on average.
Read the full abstract ▾
All authors Jiajie Wang, Yutong Zhao, Tianlin Li, Huashan Chen, Jinfu Chen, Kebin Peng, Sen He
Information Theory · Cross-listed from quant-ph
Entanglement-of-formation potentials for feedback-assisted classical communication and randomness distillation
Mark M. Wilde
We develop
entanglement-of-formation potentials for feedback-assisted classical communication and one-way randomness
distillation. For a finite-dimensional
quantum channel without initial shared
entanglement, an exact amortization
theorem bounds the increase of message information plus
entanglement remaining across the communicating laboratories. This proves a classical-feedback capacity bound using a mixed-convex-roof expression previously studied by Winter and Yang in the context of potential capacities. We determine the capacity of flagged mixtures of noiseless and
entanglement-breaking channels, improve a published depolarizing-channel converse, and evaluate the new bound exactly for the amplitude damping channel. A state analogue gives a finite-blocklength upper bound on the net shared randomness obtainable with one-way classical communication. Amplitude-damping Choi states provide exact
benchmarks, while a full-rank generalized amplitude-damping Choi state demonstrates a useful improvement where we do not evaluate the operational rate exactly. We also distinguish one-way from two-way randomness
distillation: a two-round weak-measurement protocol strictly exceeds the exact one-way rate of every nontrivial
qubit isotropic state. The protocol preserves
quantum side information during its first decoding and extracts additional randomness in the reverse direction. This shows why the one-way state potential is not a general two-way converse. Together, these results establish a common
entanglement-based approach to sharper communication and randomness bounds, while revealing how retained
quantum correlations enable two-way
distillation to surpass one-way limits.
Read the full abstract ▾
Computation and Language
Cluster Validation Indices as Self-Supervised Objectives for Text Representation Learning
Kishor Kumar Bhaumik, Nicolas Roque dos Santos, Neil Shah et al. (+2 more)
Self-supervised fine-tuning refines the
embedding space of a pretrained
language encoder without labels. However, the commonly used approaches are computationally expensive. Specifically, contrastive learning-based methods need multiview data and in-batch negative examples, while negative-free approaches require auxiliary graphs/networks. An interesting question arises: can self-supervised fine-tuning be done without relying on either additional negatives or graph data? To answer this question, we introduce SilK (Silhouette-guided K-means), which trains on a Cluster Validation Index, an internal measure of cluster quality without using labels. SilK clusters the corpus and then regresses a simplified silhouette toward a target value. Each document is compared only against the k cluster centroids, never against other documents, so the method needs no augmentation, no negative pairs and one view per document. On BERT-base, SilK trains 1.46x faster per epoch than the fastest baseline we evaluate and uses 45.4% less peak GPU
memory than the leanest one. Under frozen-encoder linear probing, SilK stays competitive with the best baselines on three downstream tasks.
Read the full abstract ▾
All authors Kishor Kumar Bhaumik, Nicolas Roque dos Santos, Neil Shah, Jia Chen, Evangelos E. Papalexakis