Computation and Language
TrajLong: Co-Designing Agentic and Long-Context Supervision for Mid-Training
Miao Peng, Qintong Zhang, Nuo Chen et al. (+8 more)
LLM
agents for coding, search, and workplace tasks increasingly rely on long-context capabilities to effectively aggregate and reason over extended interaction histories. Recent work has incorporated
agent trajectories into mid-training stage, drawing on their naturally long and interaction-rich structure. Yet how to organize the information within these trajectories into effective mid-training supervision remains underexplored. In this work, we investigate the relationship between long-context and
agent atomic capabilities and introduce TrajLong, a novel framework that compiles trajectories into long-context training tasks with dense supervision, targeting three representative atomic capabilities: evidence grounding, cross-evidence aggregation, and temporal state maintenance. We mid-train Qwen3-14B-Base and Qwen3-30B-A3B-Base with data compiled by TrajLong, followed by supervised fine-tuning. Experiments on 6 long-context and 12
agent benchmarks demonstrate broad performance gains, with controlled ablations showing improvements over raw and masked trajectory baselines. Capability-level analyses further reveal task-dependent associations between long-context and
agent atomic capabilities. These findings suggest that the shared capability demands of long-context
reasoning and
agent execution provide a principled basis for designing mid-training data to develop downstream
agent capabilities.
Read the full abstract ▾
All authors Miao Peng, Qintong Zhang, Nuo Chen, Yuhan Li, Guochen Yan, Xinran Gu, Hongqiu Wu, Hai Wang, Lydell Huang, Wentao Zhang, Jia Li
Machine Learning
Hamiltonian Metric Learning and Energy-Based Training: A Dissipative Geometric Framework for Optimization
Sparsho Chakraborty, Mohammad Alamgir, Nishanth M et al. (+3 more)
Optimization in machine learning is usually expressed through iterative rules that update model parameters using information from the loss landscape. In this work, we study an alternative viewpoint in which parameter optimization is treated as the
evolution of a dissipative dynamical system. The model parameters are regarded as generalized coordinates, the loss acts as a potential energy, and a positive-definite metric defines the local kinetic geometry of parameter space. Starting from a variational formulation, we derive the corresponding
Hamiltonian dynamics, the
geometric force generated by a position-dependent metric, and a metric-compatible Rayleigh dissipation law. The resulting continuous system satisfies a monotonic energy-dissipation relation, while its discrete form allows the influence of
curvature on the optimization trajectory to be studied directly. We illustrate the framework using a controlled CIFAR-10 image-reconstruction problem for which the optimum is known analytically. With the image Hessian used as the metric, the
curvature dependence of the quadratic modal dynamics is removed. We then reparameterize the same image as a
matrix product state, producing a genuinely position-dependent metric and a nonzero
geometric force. Poincaré return maps provide a complementary phase-space view of the resulting contraction dynamics. These examples establish HAMLET as a
geometric, energy-based framework for studying optimization as dissipative motion in parameter space. On a five-seed MNIST MLP
benchmark, HAMLET attains the highest mean test accuracy (97.95%) and the lowest mean test negative log-likelihood (0.0696) among the three evaluated optimizers.
Read the full abstract ▾
All authors Sparsho Chakraborty, Mohammad Alamgir, Nishanth M, Akshit Nanda, Ram Prasad Padhy, Sayan Mukherjee
Machine Learning
One Token Can Be Enough: Bridging Prompting and Activation Steering with Prefix Steering
Xudong Zhu and Zhihui Zhu
Prompting guides
language model behavior through the initial context, whereas activation steering often intervenes throughout generation. A natural question is whether steering can produce effects on subsequent computation similar to those of prompting. Under fixed-state
attention assumptions, we establish sufficient conditions for single- and multi-
token steering to match
prompt-induced
attention-head outputs, and characterize how changes in input representations affect this match and its approximation error. This
attention-level connection leads us to ask whether, at the behavioral level, steering can also guide subsequent generation through a brief initial intervention. We study Prefix Steering, which applies existing steering directions and operators over a short span starting at the final
prompt token, with no further direct intervention afterward. We examine how intervention duration and strength jointly shape the control-capability trade-off. Across four models and five tasks, intervention over a short span, even a single
token, often retains much of full steering's behavioral control while better preserving general capabilities, offering a trade-off competitive with, and in some settings better than, prompting and alternative steering-strength policies. Prefix Steering also remains effective on final-answer formatting tasks after
reasoning, suggesting that a brief initial intervention can influence behavior expressed well after steering ends. These findings challenge the common practice of steering every generated
token and motivate a more dynamical view of activation steering, in which a brief intervention can alter the trajectory of subsequent generation without continued intervention.
Read the full abstract ▾
Artificial Intelligence
BACAM: Behavior-Aware Continual Agent Merging for Multi-Turn Interaction
Shuaitong Li, Baochen Xiong, Xiaoshan Yang et al. (+4 more)
Model merging offers a way to integrate the capabilities of specialized experts, but existing
agent merging methods typically require all of them to be available at once. We study continual
agent merging, which integrates incoming experts sequentially without retaining previously merged experts. Yet merging in parameter space or feature subspaces does not ensure that the merged model acquires an incoming expert's behavior on interaction trajectories. Moreover, updates toward a new expert can disrupt the merged model's previously integrated interactive behavior. Therefore, we propose Behavior-Aware Continual
Agent Merging (BACAM), which learns parameter-wise merging gates from candidate-generated trajectories using expert-guided behavioral supervision. Task-level stability-plasticity control and tensor-level conflict-aware update budgets limit interference with existing capabilities while allowing new ones to be acquired. The learned gates are folded into the model weights without additional inference-time parameters. Across four interactive tasks - web shopping, tool use, information
retrieval, and
embodied interaction - BACAM achieves an average success rate of 62.82%, exceeding the strongest evaluated merging baseline by 21.69 percentage points. Our code is publicly available at https://github.com/shuaitongli/BACAM.
Read the full abstract ▾
All authors Shuaitong Li, Baochen Xiong, Xiaoshan Yang, Xizhe Zheng, Yifan Xu, Jianhao Huang, Changsheng Xu
Machine Learning
MAGIC: Topology-Aware Analytic Graph Few-Shot Class-Incremental Learning
Junlin Chen, Yuhan Wang, Xuefei Wang et al. (+3 more)
Graph few-shot class-incremental learning (GFSCIL) requires a model to continually recognize emerging classes from only a few labeled nodes while preserving previously acquired knowledge. Beyond the catastrophic forgetting inherited from conventional graph continual learning, GFSCIL presents two distinctive challenges: extremely limited novel-class supervision causes severe overfitting, while cross-session edges—edges connecting newly arriving nodes with historical nodes—alter historical propagation neighborhoods and thereby induce representation drift. We propose MAGIC, a replay-free GFSCIL framework that combines a frozen graph representation backbone (e.g., an intrinsically parameter-free backbone such as SGC or a pretrained graph foundation model) with closed-form analytic continual learning. To alleviate novel-session overfitting, MAGIC learns a topological prior from the base graph that can characterize both homophilous and heterophilous relations, and injects this prior through Potts Markov random field inference to refine supervision for novel classes. To mitigate representation drift, MAGIC transfers previous predictions from the old representations of affected historical nodes to their updated representations through drift-aware analytic
distillation. Experiments across five
datasets and eight baselines demonstrate the effectiveness of MAGIC. Under the 5-shot setting, MAGIC improves Mean Accuracy and Final Accuracy by 5.48 percentage points and 9.33 percentage points on average, and reduces Performance Drop by 10.78 percentage points on average compared with the best baselines. MAGIC also shows clear advantages under the 1- and 3-shot settings, with larger gains as the number of supports increases. Moreover, MAGIC requires substantially less training time.
Read the full abstract ▾
All authors Junlin Chen, Yuhan Wang, Xuefei Wang, Xiao Wang, Ruijie Wang, Jianxin Li
Computation and Language
Building LLM Agent Systems the Deep Learning Way: From Modular Design to Architecture Search
Tao Feng, Pengrui Han, Zhongjie Dai et al. (+1 more)
Large
Language Models (LLMs) have revolutionized AI research and enabled exciting
agent systems. To build a complex LLM
agent system, most existing research relies on insights from other domains or heuristics to manually build the
agent system. However, this approach often requires heavy hand-engineering and fails to fully optimize for the downstream task of interest. Inspired by the tremendous success of deep learning, we propose to construct LLM
agent systems in a modular manner, similar to building a deep neural network. Our key insight is to make analogies between LLM building blocks, such as
retrievals,
memories, and prompting strategies, and the successful deep learning modules, such as MLPs,
attention, and recurrent modules. We further design forward inference and feedback mechanisms for LLMs, where
prompts in LLMs are considered as the weights in deep models, and the
prompt optimization from feedback is analogous to the back-propagation
algorithm. We additionally leverage a search
algorithm to search for the best configuration of LLM
agent systems, similar to the neural architecture search (NAS) in deep learning research. Comprehensive experimental results demonstrate that the proposed deep learning recipe for LLM
agent systems is highly effective, in particular: (1) Organizing LLM modules into deep-learning-style architectures yields noticeable performance gain; (2) Automatic
prompt optimization, equivalent to backpropagation, is efficient in incorporating feedback from the task of interest and achieves at least 5% performance improvement; (3) NAS equivalent
algorithm works well for further optimizing the LLM
agent system architecture with 11% performance gain compared with randomly designed architectures. Overall, our research demonstrates the exciting opportunity of transferring the success of deep learning to building LLM
agent systems.
Read the full abstract ▾
All authors Tao Feng, Pengrui Han, Zhongjie Dai, Jiaxuan You
Computational Engineering
AlphaPADI: Formulaic Alpha Discovery via Pool-Aware Hierarchical Discrete Diffusion
Yanzheng Jin, Pengyang Shao, Yunshan Ma et al. (+5 more)
Formulaic alpha discovery seeks symbolic expressions that predict cross-sectional asset returns. In deployment, multiple formulas are combined into an alpha pool, where each formula is valued through the complementary information it contributes to joint predictive performance. While Reinforcement Learning and Generative Flow Networks have emerged as promising paradigms for generating formulaic alphas, existing frameworks face three related challenges. First, generating formulas individually leaves pool context and inter-formula complementarity outside the generative state. Second, formula-wise generation lacks a unified mechanism for preserving and revising structures at different levels. Third, pool-level rewards jointly reflect predictive performance and redundancy but cannot be differentiated directly through symbolic evaluation to train the generator. To overcome these challenges, we introduce AlphaPADI (Formulaic Alpha Discovery via Pool-Aware Hierarchical Discrete
Diffusion), a novel framework built around three components: (1) grammar-constrained buffer initialization that constructs syntactically valid pool candidates, (2) pool-aware hierarchical
diffusion that reconstructs complete pools at multiple structural scales under the current pool context, and (3) reward-guided pool refinement that evaluates joint predictive performance and inner diversity, updates the elite buffer, and trains the reverse model through reconstruction and preference learning. Empirical results on the Chinese and U.S. stock
markets demonstrate that AlphaPADI outperforms the evaluated baselines in both predictive and portfolio performance, thereby validating pool-aware generation as an effective framework for automated alpha discovery.
Read the full abstract ▾
All authors Yanzheng Jin, Pengyang Shao, Yunshan Ma, Haowen Pan, Naixin Zhai, Chen-Hui Song, Fei Shen, Kenji Kawaguchi
Machine Learning
Trinity: One Differentiable Physics for Training, Refining and Scoring Generative Floorplanners
Shih-Ying Yeh, Tzu-Sian Wang, Xuehai Wang et al. (+7 more)
Floorplanning arranges the blocks of a chip and decides their shapes under objectives that press blocks together, short wirelength and a small outline, and constraints that hold them apart, non-overlap, clusters, MIB shapes and boundary blocks. Recent
diffusion placers train on reference layouts alone and leave this coupled system to guidance, post-hoc loops and a legalizer, reporting only the endpoint, which hides what the generator contributes. We re-implement four of them under one recipe on FloorSet, score raw, refined and legalized layouts on one scale, and propose Trinity, a flow-matching floorplanner whose six differentiable functions for the constraints and objectives are its training loss term, the energy of a closed-form refiner after sampling and the base of a soft cost for every stage. The network thus learns the correction prior placers apply in their samplers, and sampling needs no guidance. Stage by stage, the training term lowers a plain
transformer's raw soft cost by 26% and matters most at short budgets, the shared refiner decides more of the final cost than the generator and matches a ported placer's loop in 16 to 660 times fewer steps, Trinity's refined soft cost is 36% below the best ported pipeline, the soft cost ranks settings as the contest's hard cost does, and on the FloorSet val set the pipeline reaches a mean hard cost of 1.014 in 1.63 s per case.
Read the full abstract ▾
All authors Shih-Ying Yeh, Tzu-Sian Wang, Xuehai Wang, Jia-Hua Lee, Daniel Z. Kaplan, Ming-Qi Xu, Wuqian Tang, Chun-Yao Wang, Shang-Hong Lai, Chun-Yi Lee
Computation and Language
From Overloaded to Guaranteed: High-Throughput Multi-SLO Enforcement for LoRA-Assisted On-Premise LLM Deployment
Zeshen Zhang, Han Zhao, Weihao Cui et al. (+9 more)
As Large
Language Models (LLMs) become essential in
privacy-sensitive sectors like hospitals and government agencies, the on-premise LLM servers offer a cost-effective and secure alternative to public cloud services. However, these resource-constrained servers struggle to guarantee heterogeneous Service Level Objectives (SLOs) when serving multiple LoRA-adapted services simultaneously. Existing serving frameworks suffer from severe SLO violations due to the computational overhead of LoRA layers and the rigid nature of batch scheduling. To address this, we propose
HALO, a scheduling method tailored for LoRA-assisted on-premise LLM deployment.
HALO introduces two key innovations: a spatial multiplexing strategy that overlaps Base and LoRA computations by partitioning GPU Streaming Multiprocessors (SMs), and an SLO-aware scheduler that decouples request execution based on "request-level slack." By prioritizing urgent tasks and utilizing idle budget for traffic shaping,
HALO significantly mitigates resource contention. Our evaluation demonstrates that
HALO minimizes SLO violations while improving throughput compared to state-of-the-art baselines.
Read the full abstract ▾
All authors Zeshen Zhang, Han Zhao, Weihao Cui, Quan Chen, Yu Liu, Yongjun Deng, Jing Yang, Jiuchen Shi, Chen Chen, Youmin Chen, Yu Feng, Minyi Guo
Artificial Intelligence · Cross-listed from eess.SP
Kapture: Capturing Cardiac Dynamics with Koopman-Governed Learning for Efficient Radar-Based Electrocardiogram Recovery
Tong Wu, Jing Peng, Ziqi Feng et al. (+1 more)
Millimeter-wave (mmWave) radar enables unobtrusive, contactless electrocardiogram (ECG) reconstruction for cardiac monitoring. Time-frequency spectrograms preserve fine cardiac patterns but often require large backbones to separate ECG-relevant features from respiration, motion, multipath, and subject-dependent interference. We propose Kapture, a parameter-efficient Koopman-governed framework that projects radar hidden states into a low-dimensional observable space and identifies a regularized full linear
evolution operator from adjacent observable states. The Koopman-predicted observables refine subsequent hidden states for ECG reconstruction. To suppress predictable interference dynamics, a temporal contrastive objective pulls neighboring states together and separates non-neighbors, while reconstruction supervision preserves task relevance. Using approximately 80 minutes of quasi-static radar-ECG recordings containing realistic noise from body movements and other sources, Kapture consistently improves reconstruction across matched backbone widths, with the largest gains under aggressive compression. The compact configuration approaches the full-width reference accuracy with 68.1% fewer parameters and 91.3% fewer profiler-covered floating-point operations (FLOPs), while the full-width configuration delivers the strongest overall reconstruction performance. Our code will be made publicly available after potential publication.
Read the full abstract ▾
All authors Tong Wu, Jing Peng, Ziqi Feng, Yuanyuan Zhang
Machine Learning
EDISCO: Equivariant DIScrete Diffusion for Euclidean Combinatorial Optimization
Ruogu Chen and Jie Han
Euclidean combinatorial optimization problems (ECOPs), such as the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP), possess inherent
symmetries under the two-dimensional Euclidean group E(2), including rotations, reflections, and translations. Existing learning-based methods, including recent
diffusion-based methods, rely on data augmentation or regularization to approximate E(2)-equivariance. This paper presents EDISCO, the first discrete
diffusion model for ECOPs with exact E(2)-invariant generative distributions over node-index solutions. EDISCO introduces an E(2)-equivariant edge-score network coupled with a categorical continuous-time Markov chain over discrete edge variables, and exact posterior sampling provides efficient multi-step inference. This design gives EDISCO a local
geometric inductive bias: edge neighborhoods with the same relative geometry and combinatorial context are represented consistently regardless of absolute position or orientation, making learning more efficient and inference more robust than non-equivariant methods. EDISCO outperforms previous learning-based state-of-the-art solvers on synthetic TSP from 100 to 10000 nodes and CVRP from 50 to 2000 customers, while using only 33-50% of the training instances. Trained only on uniform synthetic data, EDISCO also outperforms competing learning-based baselines under spatial distribution shift and CVRP constraint-tightness shift. Code is available at https://github.com/ValleyC/EDISCO.
Read the full abstract ▾
Computational Complexity · Cross-listed from quant-ph
Gap Amplification for Local Hamiltonians with Combinatorial Soundness
Mitali Bafna, Quynh T. Nguyen and Tina Zhang
The
quantum PCP
conjecture is one of the major open problems in
quantum complexity theory. It has resisted attack in part because many primitives used in the proof of the classical PCP
theorem, such as locality-preserving gap amplification and alphabet reduction, have no obvious
quantum analogues due to
quantum no-cloning. Locality-preserving gap amplification is a procedure that takes as input a local
Hamiltonian problem instance and produces a new instance with a larger promise gap, without increasing the locality of the
Hamiltonian, and instead moderately increasing its local qudit dimension. Obtaining this kind of control over the locality during gap amplification is critical to the success of many known strategies for proving the classical PCP
theorem. In this work, we put forth the first known viable template for
quantum locality-preserving gap amplification, and we prove that our procedure amplifies the combinatorial gap of local
Hamiltonians. Our work introduces a new framework for
reasoning about
quantum gap amplification in terms of fault-tolerant computation, and illuminates a route toward importing one of the central ingredients in classical PCPs into the
quantum setting. In particular, we build upon ideas from the recent classical PCP of Bafna–Minzer–Vyas based on high-dimensional expanders, and the
circuit-to-
Hamiltonian construction of Anshu–Breuckmann–Nguyen, in addition to several recent advances in
quantum coding theory.
Read the full abstract ▾
Performance
LLBPE: Linked-List Based GPU-Parallel BPE Tokenizer
Aditya Kovilur, Varun Chandra Shekar and Ariful Azad
Every LLM inference begins with tokenization, which converts raw input bytes into the discrete
token sequence the model consumes. For text, this step is often implemented using Byte Pair Encoding (BPE), an
algorithm originally introduced for data compression. BPE has traditionally run on the CPU with extensive optimization, but recent work has moved it to the GPU for higher throughput. We show that these GPU implementations are bottlenecked not by computation but by data movement. We develop LLBPE that represents the
token sequence as an array-based linked list so that each merge reduces to a constant- time pointer update. Furthermore, LLBPE fuses rank lookup, minimum selection, and merging into a single kernel to eliminate redundant hash map queries. LLBPE achieves up to 5.2x higher throughput than the best existing GPU implementation and 24.6x over optimized CPU implementations, at the cost of minor discrepancies in tokenized output.
Read the full abstract ▾
Machine Learning
How Should Teachers Be Prepared? RL on Student-Induced States for On-Policy Distillation
Xiaoyu Ma, Haoyue Liu, Zhichao Wang et al. (+2 more)
On-policy
distillation (OPD) improves the
reasoning capabilities of small
language models through
token-level teacher supervision on student-generated trajectories. Yet can teachers that excel at solving problems independently also guide student
reasoning effectively? Prior work shows that when student prefixes follow
reasoning paths that differ from the teacher's own or contain errors, teachers can be less accurate when continuing from these prefixes than when solving problems independently. To this end, we propose Prep-OPD, which uses reinforcement learning (RL) before
distillation to train the teacher to adapt to the student's existing
reasoning state and correct course when errors arise. Training optimizes teacher continuations from fixed student prefixes using final-answer correctness as the reward. The prepared teacher then trains the student through trajectory guidance and
token-level supervision. We evaluate Prep-OPD on eight mathematical
reasoning benchmarks, using Qwen3-4B-Instruct-2507 as the teacher and Qwen3-0.6B and Qwen3-1.7B as students. With the 4B teacher and 1.7B student, Prep-OPD improves average accuracy over standard OPD and the strongest baseline, Relay-OPD, by 8.28 and 2.30 percentage points, respectively. Controlled experiments further show that teacher RL conditioned on student-generated prefixes yields higher student accuracy than problem-start teacher RL with and without handoff on Qwen3-1.7B. Reusing the same prepared teacher also improves Qwen3-0.6B.
Read the full abstract ▾
All authors Xiaoyu Ma, Haoyue Liu, Zhichao Wang, Jionghao Zhu, Xiaoying Tang
Robotics
A Unified Dynamics Framework for Reinforcement Learning and Classical Control of a Six-DOF Pipeline-Tracking ROV in NVIDIA Isaac Sim
Cheng Siong Chin, M. Venkateshkumar and Jianhua Zhang
Reinforcement learning controllers for
underwater vehicles are usually trained against one physics representation and deployed against another, so reported performance does not always describe behavior outside training. This paper presents a pipeline-tracking architecture for a six-degree-of-freedom remotely operated vehicle (ROV) in which one Universal Scene Description (USD) scene supplies the real BlueROV2-Heavy mass, added-mass, damping, buoyancy, and thruster parameters to both halves of the system: a vectorized NumPy implementation of Fossen's marine-craft equations, and an interactive NVIDIA Isaac Sim deployment applying the identical equations as PhysX forces at every step. The Coriolis-centripetal term is the primary dynamics model in both branches; a controlled ablation on PPO and TRPO shows that including it does not destabilize either
algorithm and modestly improves tracking, about 19 percent lower standoff RMS error for TRPO. Five reinforcement learning
algorithms, PPO, soft actor-critic, TD3, DDPG, and TRPO, are trained against one environment, reward, and randomized evaluation harness through a checkpoint-compatibility layer scoring any policy with the same code. The pipeline is extended with six classical baselines, PID, sliding-mode, fuzzy logic, feedback linearization, model predictive control, and an adaptive neuro-fuzzy inference system, driven by the same guidance geometry and thruster allocation as the learned policies. Under Coriolis-enabled dynamics, PPO, TRPO, and feedback linearization reach the strongest combination of 100 percent success and competitive accuracy; PID, fuzzy control, and the neuro-fuzzy baseline also reach 100 percent success with looser tracking; DDPG and TD3 each show a specific, explainable failure mode rather than a general weakness of off-policy learning; and classical control remains a strong baseline against the best learned policies.
Read the full abstract ▾
Game Theory · Cross-listed from math.OC
Social Optimality Does Not Imply Coalitional Stability in Unweighted Max-k-Cut Games
Hritiz Gogoi
In Max-$k$-Cut games, optimal colorings maximize social welfare, but are they stable against coordinated deviations that strictly benefit every participating player? A recurring
conjecture in the literature asserts that, for unweighted graphs, every optimal coloring has this stability property, known as strong
equilibrium. We disprove the
conjecture for every $k\ge3$ by exhibiting a finite, simple, connected, unweighted graph with an optimal coloring that is not a strong
equilibrium. The profitable coalitional deviation leads to another optimal coloring: every coalition member gains, while players outside the coalition bear the corresponding losses and social welfare remains unchanged. We also give an exact identity relating coalitional gains, changes in cut value, and internal conflicts, recovering the known stability guarantee for optimal colorings when the maximum degree is at most $2k-1$. For strong deviations from general Nash
equilibria, we establish a sharp upper bound on the number of monochromatic edges remaining within the coalition and show that this number can exceed the coalition size.
Read the full abstract ▾
Machine Learning
Bridging the EHR Divide: Asymmetric Contrastive Learning for Cross-National Medical Representation Transfer
Qingyang Zhang
Cross-system transfer of longitudinal Electronic Health Record (EHR) representations is challenging because clinical coding, patient populations, and healthcare workflows differ substantially across institutions and countries. We introduce Asymmetric Supervised Contrastive Learning (Asymmetric SupCon), a task-specific pre-training objective motivated by the heterogeneity of negative clinical outcomes. The objective clusters patients sharing a target positive outcome without explicitly attracting negative trajectories toward one another. We pre-train temporal
Transformer encoders on longitudinal records from 3.98 million patients in the Taiwanese National Health Insurance Research Database (NHIRD) and transfer them to two U.S. EHR
datasets, MIMIC-IV and EHRSHOT. A hybrid semantic mapping pipeline combining direct mappings with
embedding-based
retrieval enables transfer across heterogeneous clinical vocabularies. On MIMIC-IV, NHIRD pre-training consistently improves over random initialization while substantially narrowing the performance gap to task-specific in-domain pre-training. On EHRSHOT, the transferred models show particularly strong few-shot performance for incident disease prediction. A controlled objective ablation under a matched pre-training scale shows that Asymmetric SupCon achieves higher mean AUPRC than direct supervised BCE transfer on all four evaluated tasks and Standard SupCon on three of four, with a 0.003 AUPRC deficit on readmission. These results support asymmetric contrastive pre-training as an effective approach for task-specific cross-national EHR representation transfer. Code is available at https://github.com/qingYzhang/Asymmetric_SupCon.
Read the full abstract ▾
Machine Learning
TempoBridge: Source-Conditioned Flow Matching with Optimal Transport Couplings for Single-Cell Population Transitions
Bowen Han, Lingbei Meng, Shihuan Luo et al. (+7 more)
Destructive single-
cell measurements provide unpaired population snapshots rather than observations of the same
cells across conditions. Local
cell states and transition requests may also be insufficient to distinguish responses across source populations. We introduce TempoBridge, a common source-conditioned transport formulation for temporal, genetic, and chemical population transitions. Source
cells initialize latent transport and provide a fixed empirical population summary. The velocity field receives this summary alongside the evolving
cell state, flow time, and a structured transition descriptor. Minibatch optimal transport (OT) supplies couplings only for conditional flow-matching training paths; inference requires neither target expression nor OT computation. On held-out donors, TempoBridge achieves an Energy distance of 0.129 versus 0.144 for scGen. Genetic mean-expression $L_2$ error is 2.261 versus 3.156 for scGPT-scratch under Seen 2/2. On held-out compounds, condition-averaged drug-effect correlation is 0.598 versus 0.561 for the CellFlow adapter. Temporal ablations show higher mean distributional error after removing source context, replacing optimal transport with random pairing, or replacing flow matching with static residual regression. Together, these results demonstrate the predictive utility of a common source-conditioned transport formulation across held-out donors, gene combinations, and compounds.
Read the full abstract ▾
All authors Bowen Han, Lingbei Meng, Shihuan Luo, Yupeng Zang, Wenlin LI, Peize He, Yaodi Luo, Lian Zhang, Jianqing Zhu, Jinchao Xu
Machine Learning · Cross-listed from math.OC
Near-Optimal Complexity of Finite-Sum Nonconvex-Strongly-Concave Minimax Optimization
Qihao Zhou
We characterize, up to logarithmic factors, the minimax expected query complexity of finite-sum nonconvex-strongly-concave optimization under mean-squared averaged smoothness. For randomized zero-respecting incremental first-order
algorithms, the complexity is $\tilde{\Theta}(n+\min\{\sqrt{n}\,\kappa,n^{3/4}\sqrt{\kappa}\}\,L\Delta\varepsilon^{-2})$ throughout $\kappa=L/\mu\ge1$, under exact dual initialization and for $0<\varepsilon^2\le c_0L\Delta$, where $c_0>0$ is universal. This characterization is our main result. A dual-chain construction provides the lower bound and matches the existing Catalyst upper bound for $\kappa\ge\sqrt{n}$. For $1\le\kappa\le\sqrt{n}$, we introduce recursive proximal descent-ascent (RPDA), which retains a recursive gradient
estimator across proximal subproblems and attains $\tilde{O}(n+\sqrt{n}\,\kappa L\Delta\varepsilon^{-2})$ with a fixed query budget. Both upper bounds guarantee an expected squared primal gradient at most $\varepsilon^2$. Under individual smoothness, we also prove $\Omega(n+\min\{\kappa,\sqrt{n\kappa}\}\,L\Delta\varepsilon^{-2})$ for every $\kappa\ge1$. It matches the
polynomial upper rate for a bilinear subclass when $\kappa\ge n$; the intermediate-condition-number gap remains open.
Read the full abstract ▾
Artificial Intelligence
Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning
Jing Xie, Haochen Yuan and Yunbo Wang
Time-series question answering (TSQA) requires grounding linguistic queries and diverse answer formats in complex numerical observations. However, existing methods heavily overfit to specific
datasets and struggle to generalize when input series, question contexts, and answer requirements shift simultaneously. To address this challenge, we propose TSHarness, an agentic framework that establishes a decoupled workflow for cross-
dataset zero-shot TSQA. At its core, TSHarness divides and conquers numerical perception and contextual
reasoning via a structured Time-Series Perception State (TPS). Guided by a reusable
memory of analytical knowledge, a learned Tool Selector adaptively invokes numerical tools to extract salient statistical and temporal features into the TPS. The answering
agent then performs semantic
reasoning over the TPS to generate target outputs, triggering iterative re-perception through the feedback loop when evidence is deemed insufficient. By separating numerical feature extraction from question-specific
reasoning, TSHarness eliminates the need for target-side training or answer feedback, providing a generalizable, cost-efficient foundation for zero-shot TSQA.
Read the full abstract ▾
Machine Learning
Software World Models: From Consequence Prediction to Decision Value
Tongli Su, Yuntong Hu, Liang Zhao et al. (+3 more)
A coding
agent may safely modify one repository while silently breaking downstream services, libraries, or datastores that depend on it. Exhaustively running integration tests after every
agent action is impractical, so the
agent must predict these failures before executing them. Existing software world models predict the
agent's own observations, while static change-impact analysis only identifies where a change may propagate. We instead introduce the Software World Model (SWM), which models the broader system affected by a code change and predicts its blast set: the components that the change will break. SWM follows three stages: explore, learn, and act. Explore executes candidate changes from restored system states, prioritizing regions where observed failures contradict the dependency graph. Learn fine-tunes a
language model on these execution outcomes to predict downstream breakage. Act converts sampled predictions into per-consumer break probabilities for change ranking, proactive migration, and deciding when another execution is worth its cost. On held-out synthetic systems, SWM improves blast-set F1 from 0.431 for static reachability to $0.571\pm0.037$, more than halves ranking regret, and improves migration return at all nine evaluation checkpoints. The two methods are complementary: reachability is stronger on dependencies represented in the graph, while SWM recovers failures caused by couplings the graph misses. Experiments on held-out real libraries further show that predicting structured failure outcomes, rather than only scalar risk, is important for downstream decision quality.
Read the full abstract ▾
All authors Tongli Su, Yuntong Hu, Liang Zhao, Bowen Zhu, JayaSai Somasundaram, Hasibul Haque
Machine Learning
A Graph-Based Inspection and Intervention Tool for Assessing Mechanistic Learning in PINNs
Adwait Patkhedkar, Alifaraz Lakhani, Prathmesh Mohite et al. (+1 more)
We ask whether physically meaningful correspondences discovered inside a trained scientific model remain meaningful outside the conditions under which they were discovered. We introduce GIIT (Graph-based Inspection and Intervention Tool), which represents governing physics as a computational physics dependency graph, maps graph nodes to internal network components via sensitivity- and trend-based discovery, and tests the resulting mapping under targeted intervention. Evaluating on temporal extrapolation out-of-distribution (OOD) regimes of increasing severity, we find that temporal extrapolation is associated with layer-wise correspondence drift and reduced functional correspondence. Specifically, while the model achieves low physics residual in-distribution (1.915 x 10-4 on full ID and 1.01 x 10-4 on an ID sub-window t in [0.5, 0.8]), the functional mapping changes even before leaving the training domain, and the shift continues as the evaluation window extends beyond the training domain: residual error increases from 2.81 x 10-2 on the boundary-crossing window (t in [0.5, 1.5]) to 3.30 x 10-1 on severe OOD (t in [1, 2]), accompanied by a systematic leftward shift of internal layer mappings, where the average winner layer index drops from 5.71 (ID) to 3.00 (ID sub-window) down to 2.29 (severe OOD). Only 2 of 7 physical nodes maintain stable layer assignments across the boundary-crossing window, and only 1 of 7 under severe extrapolation, revealing potential internal functional correspondence changes before severe degradation in conventional output metrics. Additional results for linear oscillatory systems are further detailed in the appendix.
Read the full abstract ▾
All authors Adwait Patkhedkar, Alifaraz Lakhani, Prathmesh Mohite, Abhijeet Salunke
Machine Learning
D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform
Jieke Wu, Qijie Zhu, Weimin Wu et al. (+3 more)
We propose D-DOIT (Discrete Doob-Oriented Inference-time Transformation), a training-free and efficient adaptation method for discrete
diffusion models with generic rewards. D-DOIT formulates adaptation as sampling from a reward-tilted target distribution and realizes this transport through Doob's h-transform of the discrete
diffusion reverse kernel, using only reward values rather than reward gradients. Unlike continuous
diffusion, masked discrete
diffusion samples categorical
token-reveal transitions rather than continuous state updates. D-DOIT derives the corresponding discrete Doob's h-transform, which guides sampling by reweighting reverse transition probabilities instead of adding a drift correction. To make this transformation practical, D-DOIT avoids expensive future rollouts. At each guided step, D-DOIT samples candidate next states, uses the model prediction head to complete each candidate into a clean sequence, evaluates each completion with the reward oracle, and resamples the next state with probabilities proportional to the rewards. An optional late-stage best-of-K refinement further improves sample quality by branching trajectories only near the end of denoising, avoiding the $K$-fold cost over the full trajectory. Empirically, across regulatory DNA design and
protein inverse folding
benchmarks, D-DOIT outperforms training-free guidance baselines. It improves enhancer activity and
cell-type specificity while preserving sequence naturalness, and achieves the highest success rate in
protein inverse folding.
Read the full abstract ▾
All authors Jieke Wu, Qijie Zhu, Weimin Wu, Zeqi Ye, Minshuo Chen, Han Liu
Multiagent Systems
Orchestrating Level-$K$ Policies Against Unknown Opponents in Partially-Observable Dynamic Games
Addison Kalanther, Sanika Bharvirkar, Daniel Bostwick et al. (+2 more)
Level-$K$
reasoning generates a hierarchy of policies specialized to opponents with different
reasoning levels. When an opponent's level is unknown, a common deployment rule estimates that level and selects the corresponding response. In a dynamic, partially-observed game, this selection is repeated, with each choice shaping subsequent states and observations. The response associated with the most likely opponent level need not maximize expected return from the current history. We formulate this deployment problem as dynamic orchestration of a fixed, pretrained policy library in a partially observable Markov game. We compare classification-based orchestrators (CBOs) trained using offline data or on-policy data aggregation with a reinforcement-learning-based orchestrator (RLBO) trained to maximize expected discounted return. In pursuit-evasion experiments, on-policy training improves classification and return, yet RLBO achieves higher return than the on-policy and offline CBOs. Given a pretrained library, RLBO also reaches performance comparable to a policy trained directly over the pursuers' action space with fewer training timesteps. These findings support treating a hierarchy of level-$K$ policies as a resource for orchestration, not a prescription for deployment.
Read the full abstract ▾
All authors Addison Kalanther, Sanika Bharvirkar, Daniel Bostwick, Chinmay Maheshwari, Shankar Sastry
Machine Learning
Learning under Localized Minority Imbalance
Amin Hosseininasab and Steven M. Shugan
Class-imbalance methods implicitly assume that the minority class is uniformly undersampled relative to the majority class. However, in many real-world settings, minority instances may be disproportionately under-observed in certain regions of the feature space. For example, small businesses that go bankrupt may disappear from records, while those that survive remain visible, making bankruptcy appear less common among small firms than it actually is. This gives rise to localized minority imbalance (LMI), a challenge that is often overlooked and extends beyond general class-count imbalance. We show that under LMI, existing imbalance mitigation techniques can fit observation-induced biases in the training data and generalize poorly to under-observed regions of the true minority distribution. To address this, we propose a tree-based stratified approach that recursively partitions the feature space with the goal of reducing within-stratum LMI distortion. For each resulting stratum, we pair its majority instances with the full observed minority set and train a base classifier to create an ensemble. Extensive experiments over
benchmark tabular
datasets simulated with LMI show that our stratified ensembling approach outperforms popular and state-of-the-art imbalance mitigation techniques. We also introduce a gold-standard evaluation protocol that uses unbiased test sets, and demonstrate that conventional hold-out evaluation from the same LMI-biased data can substantially mislead performance. Overall, our results highlight that the cause of imbalance is as important as the correction method.
Read the full abstract ▾
Robotics
DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
Seongheon Park, Heecheol Kim, Shulin Tian et al. (+5 more)
Scaling
robot data and model capacity has improved
Vision-
Language-Action (VLA) policies, but further progress is constrained by the high cost of robotic data. Verifier-guided test-time scaling offers an efficient alternative by sampling multiple action candidates and selecting the one most likely to lead to task success at inference time. Existing classification-based verifiers learn from trajectory-level outcomes but treat all visited states equally, even though their value for candidate discrimination can vary across a trajectory. At many states, plausible actions are similar and provide limited discrimination signal, while only a sparse set of decision-critical states admits meaningfully different actions that can substantially affect downstream outcomes. To address this, we propose DiVeR, which estimates decision criticality from the dispersion of sampled action representations. DiVeR then uses this signal to reweight verifier learning toward states where action selection is most consequential, without requiring step-level annotations or additional environment interaction. Across LIBERO, RoboCasa, and real-world experiments on a Franka Research 3
robot, DiVeR consistently improves task success through more effective verifier-guided action selection, while adding negligible verifier inference overhead.
Read the full abstract ▾
All authors Seongheon Park, Heecheol Kim, Shulin Tian, Lilika Makabe, Namiko Saito, Katsushi Ikeuchi, Sharon Li, Yasuyuki Matsushita
Machine Learning
Billion-Scale Thumbnail Optimization for Uncurated Short-Form Videos via Multi-Armed Bandits
Ying Han, Ling Liu, Fabio Soldo et al. (+7 more)
This paper introduces a real-time thumbnail optimization system deployed at a global $O(B)$ scale on a major short-form
video platform. Unlike traditional long-form content, where custom thumbnails are heavily curated by creators, a considerable fraction of short-form
videos are published without human-selected artwork. To address this uncurated corpus, we present a fully automated, end-to-end framework that replaces static default frames with dynamic, data-driven selections across billions of
videos. To the best of our knowledge, this is the first published work demonstrating an online Multi-Armed Bandit framework successfully deployed at an $O(B)$ scale for uncurated short-form
video discovery. Our solution pairs a multi-stage candidate generation pipeline with a low-latency serving infrastructure. By initializing the exploration framework with image-specific priors derived from a deep visual quality model, the system minimizes exploration costs and dynamically serves optimal thumbnails at serving time. Global deployment demonstrates statistically significant improvements in core user discovery and engagement metrics.
Read the full abstract ▾
All authors Ying Han, Ling Liu, Fabio Soldo, Vu Nguyen, Danio Wang, Liz Kidd, Yongle Cao, Theodore Rose, Su-Lin Wu, Romer Rosales
Robotics
RobotUse: Allocating Computation, Context, and Decisions
Junhoo Lee, Injun Baek, Seungyeon Kim et al. (+4 more)
Robot agents must connect their intended actions to observed outcomes while retaining the context needed to revise their choices over repeated attempts. Existing interfaces often leave these choices inside predefined tools or require
agents to manage detailed execution code and its growing history. We introduce RobotUse, a
robot agent harness that organizes computation, context, and decisions around specifying and revising physical actions.
Agents visually select targets and poses, while the backend handles geometry, motion planning, and control. Subagents retain detailed interactions within each subgoal and return the information needed for subsequent decisions. Continual harnessing lets
agents learn from execution by updating a persistent playbook. On RoboLab, RobotUse achieves 45% task success, outperforming CaP-X by 6.7 percentage points while maintaining compact decision contexts and reducing reliance on predefined action abstractions. Furthermore, we show that RobotUse learns from real-world execution despite imperfect feedback and transfers what it learns to subsequent tasks. Project page is available at https://robotuse-team.github.io/.
Read the full abstract ▾
All authors Junhoo Lee, Injun Baek, Seungyeon Kim, Suhyun Jeon, Minkyu Kim, Baekseung Kim, Nojun Kwak
Machine Learning
Prompt Dominance and Asymmetric Verifier Costs: Empirical Ablations of GRPO at 1B Scale on GSM8K
Yi Hou
This paper studies GRPO at 1B scale from both directions: what
estimator choices do to the learning signal, and what a degraded reward signal does to what is learned. We train OLMo-2-0425-1B on GSM8K with a from-scratch implementation and measure both sides in controlled sweeps, including a verifier-quality experiment that degrades the training reward and the test-time selector identically. Four results stand out. The
prompt is the first-order decision: the zero-shot
prompt leaves the base model at 0.08% (its outputs are degenerate continuations, not wrong answers), so almost no group carries a gradient, and training succeeds because the 3-shot
prompt reaches 18.3%. At this scale the
estimator variants sit within seed noise, with Dr. GRPO ahead on both seeds. In the off-policy regime, clipping is the whole story: training on data without a clipped ratio loses 4-6 points relative to the on-policy reference, while GRPO-style clipping and GSPO recover the loss entirely. Finally, the same weak verifier is far cheaper in RL than in test-time selection: a 10%-flip verifier leaves RL's attainable gain intact (91% and 106% retained across two seeds) where selection retains 57%, and a format-only verifier leaves RL with 16-30% of its gain and selection with essentially nothing. Flip noise acts as an affine transform on the expected reward, and the group-normalized advantage with Adam's rescaling removes it exactly; the residual is a second-order variance effect that the matched-step comparison at a 30% flip rate tests.
Read the full abstract ▾
Software Engineering
Assembling Insights for Agentic Machine Learning Engineering Systems
Bihui Jin, Yinxi Li, Kaiyuan Wang et al. (+1 more)
Agentic machine learning engineering (MLE) is an emerging AI4SE application for complex ML tasks and a step toward recursive self-improvement of AI systems. Recent agentic MLE systems show the value of leveraging insights from related MLE tasks: some systems condition code generation on expert domain knowledge, which is implicitly curated from peer MLE tasks; some systems have a loop of solving an MLE task, gathering
memory to benefit future tasks. However, insight collection and injection remain ad hoc, and existing evaluations often do not control insight sources, making data leakage a threat to validity. To close these gaps, we systematically study how insights from related MLE tasks affect agentic MLE systems, and how their impact depends on insight type and injection method. We introduce MLE-InsightBench, a
benchmark of 160 Kaggle competitions across 12 domains. To prevent leakage, one competition per domain is held out as the target, while the remaining 148 serve as sources only when they cannot have been influenced by the target task, such as through later editions or reused solutions. We also develop MLE-InsightForge, an insight assembly
agent that explores source competitions, top human solutions, and writeups to construct three insight types: 12 domain insights summarizing best practices, 148 competition insights describing winning solutions, and 16 improvement insights capturing generic debugging and optimization strategies. These insights are injected either as on-demand skills or as an upfront playbook. In our evaluation, the extracted insights improve the normalized private-test score by 123.9% over a no-insight baseline. Controlled experiments further show that the three insight types are complementary; the better injection mode (skill vs. playbook) varies by tasks, with skills more cost-effective overall; and the gains generalize across backend LLMs.
Read the full abstract ▾
All authors Bihui Jin, Yinxi Li, Kaiyuan Wang, Pengyu Nie