Machine Learning
From Time Series to State: Situation-Aware Modeling for Air Traffic Flow Prediction
Anqi Liu, Jiangtao Zhao, Guiyuan Jiang et al. (+3 more)
Accurate air traffic prediction in the terminal airspace (TA) is pivotal for proactive air traffic management (ATM). However, existing data-driven approaches predominantly rely on time series-based
forecasting paradigms, which inherently overlook critical aircraft state information, such as real-time kinematics and proximity to airspace boundaries. To address this limitation, we propose AeroSense, a direct state-to-flow modeling framework for air traffic prediction. Unlike classical time series-based methods that first aggregate aircraft trajectories into macroscopic flow sequences before modeling, AeroSense explicitly represents the real-time airspace situation as a dynamic set of aircraft states, enabling the direct processing of a variable number of aircraft instead of time series as inputs. Specifically, we introduce a situation-aware state representation that enables AeroSense to sense the instantaneous terminal airspace situation directly from microscopic aircraft states. Furthermore, we design a model architecture that incorporates masked self-
attention to capture inter-aircraft interactions, together with two decoupled prediction heads to model heterogeneous flow dynamics across two key functional areas of the TA. Extensive experiments on a large-scale real-world airport
dataset demonstrate that AeroSense consistently achieves state-of-the-art performance, validating that direct modeling of microscopic aircraft states yields substantially higher predictive fidelity than time series-based baselines. Moreover, the proposed framework exhibits superior robustness during peak traffic periods, achieves Pareto-optimal performance under dayparting multi-object evaluation, and provides meaningful interpretability through
attention-based visualizations.
Read the full abstract ▾
All authors Anqi Liu, Jiangtao Zhao, Guiyuan Jiang, Feng Hong, Yanwei Yu, Bin Wang
Machine Learning · Cross-listed from q-bio.NC
Probabilistic Prediction of Neural Dynamics via Autoregressive Flow Matching
Nicole Rogalla, Yuzhen Qin, Mario Senden et al. (+2 more)
Forecasting neural activity in response to naturalistic stimuli remains a key challenge for understanding
brain dynamics and enabling downstream neurotechnological applications. Here, we introduce a generative
forecasting framework for modeling neural dynamics based on autoregressive flow matching (AFM). Building on recent advances in transport-based generative modeling, our approach probabilistically predicts neural responses at scale from
multimodal sensory input. Specifically, we learn the conditional distribution of future neural activity given past neural dynamics and concurrent sensory input, explicitly modeling neural activity as a temporally evolving process in which future states depend on recent neural history. We evaluate our framework on the Algonauts project 2025 challenge functional
magnetic resonance imaging
dataset using subject-specific models. AFM significantly outperforms both a non-autoregressive flow-matching baseline and the official challenge general linear model baseline in predicting short-term parcel-wise blood oxygenation level-dependent (BOLD) activity, demonstrating improved generalization and widespread cortical prediction performance. Ablation analyses show that access to past BOLD dynamics is a dominant driver of performance, while autoregressive factorization yields consistent, modest gains under short-horizon, context-rich conditions. Together, these findings position autoregressive flow-based generative modeling as an effective approach for short-term probabilistic
forecasting of neural dynamics with promising applications in closed-loop neurotechnology.
Read the full abstract ▾
All authors Nicole Rogalla, Yuzhen Qin, Mario Senden, Ahmed El-Gazzar, Marcel van Gerven
Machine Learning · Cross-listed from stat.ML
Cost-optimal Sequential Testing via Doubly Robust Q-learning
Doudou Zhou, Yiran Zhang, Dian Jin et al. (+3 more)
Clinical decision-making often involves selecting tests that are costly, invasive, or time-consuming, motivating individualized, sequential strategies for what to measure and when to stop ascertaining. We study the problem of learning cost-optimal sequential decision policies from retrospective data, where test availability depends on prior results, inducing informative missingness. Under a sequential missing-at-random mechanism, we develop a doubly robust Q-learning framework for estimating optimal policies. The method introduces path-specific inverse probability weights that account for heterogeneous test trajectories and satisfy a normalization property conditional on the observed history. By combining these weights with auxiliary contrast models, we construct orthogonal pseudo-outcomes that enable unbiased policy learning when either the acquisition model or the contrast model is correctly specified. We establish oracle inequalities for the stage-wise contrast
estimators, along with convergence rates, regret bounds, and misclassification rates for the learned policy. Simulations demonstrate improved cost-adjusted performance over weighted and complete-case baselines, and an application to a prostate cancer cohort study illustrates how the method reduces testing cost without compromising predictive accuracy.
Read the full abstract ▾
All authors Doudou Zhou, Yiran Zhang, Dian Jin, Yingye Zheng, Lu Tian, Tianxi Cai
Machine Learning
Gradient-Variation Regret Bounds for Unconstrained Online Learning
Yuheng Zhao, Andrew Jacobsen, Nicolò Cesa-Bianchi et al. (+1 more)
We develop parameter-free
algorithms for unconstrained online learning with regret guarantees that scale with the gradient variation $V_T(u) = \sum_{t=2}^T \|\nabla f_t(u)-\nabla f_{t-1}(u)\|^2$. For $L$-smooth convex losses, we provide fully-adaptive
algorithms achieving regret of $\widetilde{O}(\|u\|\sqrt{V_T(u)} + L\|u\|^2+G^4)$ without requiring prior knowledge of comparator norm $\|u\|$, Lipschitz constant $G$, or smoothness $L$. The update in each round can be computed efficiently via a closed-form expression. Our results extend to dynamic regret and find immediate implications for the stochastically-extended
adversarial (SEA) model, which significantly improves upon the previous best-known result (Wang et al., 2025).
Read the full abstract ▾
All authors Yuheng Zhao, Andrew Jacobsen, Nicolò Cesa-Bianchi, Peng Zhao
Machine Learning
A Full Compression Pipeline for Green Federated Learning in Communication-Constrained Environments
Elouan Colybes, Shirin Salehi and Anke Schmeink
Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, thereby preserving
privacy. However, FL often suffers from significant communication and computational overhead, limiting its scalability and sustainability. In this work, we introduce a Full Compression Pipeline (FCP) for FL in communication-constrained environments. FCP integrates three complementary deep compression techniques (
pruning, quantization, and Huffman encoding) into a unified end-to-end framework. By compressing local models and communication payloads, FCP substantially reduces transmission costs and resource consumption while maintaining competitive accuracy. To quantify its impact, we develop an evaluation framework that captures both communication and computation overheads as a unified model cost, allowing a holistic assessment of efficiency trade-offs. The pipeline is evaluated in an independent and identically distributed (IID) and non-IID data setting. In one representative scenario, training a ResNet-12 model on the CIFAR-10
dataset with ten clients and a 2 Mbps bandwidth, the FCP achieves more than 11$\times$ reduction in model size, with only a 2% drop in accuracy compared to the uncompressed baseline. This results in an FL training that is more than 60% faster.
Read the full abstract ▾
Machine Learning
Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)
Chenhao Fang, Jordi Mola, Mark Harman et al. (+10 more)
Although LLMs drive automation, it is critical to ensure immense consideration for high-stakes enterprise workflows such as those involving legal matters, risk management, and
privacy compliance. For Meta, and other organizations like ours, a single hallucinated clause in such high stakes workflows risks material consequences. We show that by framing
hallucination mitigation as a Minimum Bayes Risk (MBR) problem, we can dramatically reduce this risk. Specifically, we introduce a Hybrid Utility MBR (HUMBR) framework that synthesizes semantic
embedding similarity with lexical precision to identify consensus without ground-truth references, for which we derive rigorous error bounds. We complement this theoretical analysis with a comprehensive empirical evaluation on widely-used public
benchmark suites (TruthfulQA and LegalBench) and also real world data from Meta production deployment. The results from our empirical study show that MBR significantly outperforms standard Universal Self-Consistency. Notably, 81% of the pipeline's suggestions were preferred over human-crafted ground truth, and critical recall failures were virtually eliminated.
Read the full abstract ▾
All authors Chenhao Fang, Jordi Mola, Mark Harman, Jason Nawrocki, Vaibhav Shrivastava, Yue Cheng, Jay Minesh Shah, Katayoun Zand, Mansi Tripathi, Arya Pudota, Matthew Becker, Hervé Robert, Abhishek Gulati
Machine Learning · Cross-listed from cs.AI
From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning
Chen Zhan, Xiaoyu Tan, Gengchen Ma et al. (+3 more)
The integration of Large
Language Models (LLMs) into clinical decision support is critically obstructed by their opaque and often unreliable
reasoning. In the high-stakes domain of healthcare, correct answers alone are insufficient; clinical practice demands full transparency to ensure patient safety and enable professional accountability. A pervasive and dangerous weakness of current LLMs is their tendency to produce "correct answers through flawed
reasoning." This issue is far more than a minor academic flaw; such process errors signal a fundamental lack of robust understanding, making the model prone to broader
hallucinations and unpredictable failures when faced with real-world clinical complexity. In this paper, we establish a framework for trustworthy clinical argumentation by adapting the Toulmin model to the diagnostic process. We propose a novel training pipeline: Curriculum Goal-Conditioned Learning (CGCL), designed to progressively train LLM to generate diagnostic arguments that explicitly follow this Toulmin structure. CGCL's progressive three-stage curriculum systematically builds a solid clinical argument: (1) extracting facts and generating differential diagnoses; (2) justifying a core hypothesis while rebutting alternatives; and (3) synthesizing the analysis into a final, qualified conclusion. We validate CGCL using T-Eval, a quantitative framework measuring the integrity of the diagnosis
reasoning. Experiments show that our method achieves diagnostic accuracy and
reasoning quality comparable to resource-intensive Reinforcement Learning (RL) methods, while offering a more stable and efficient training pipeline.
Read the full abstract ▾
All authors Chen Zhan, Xiaoyu Tan, Gengchen Ma, Yu-Jie Xiong, Xiaoyan Jiang, Xihe Qiu
Machine Learning · Cross-listed from cs.RO
AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps
Liaoyuan Fan, Zetian Xu, Chen Cao et al. (+3 more)
Pretrained
video generation models provide strong priors for
robot control, but existing unified world action models still struggle to decode reliable actions without substantial
robot-specific training. We attribute this limitation to a structural mismatch: while
video models capture how scenes evolve, action generation requires explicit
reasoning about where to interact and the underlying manipulation intent. We introduce AIM, an intent-aware unified world action model that bridges this gap via an explicit spatial interface. Instead of decoding actions directly from future visual representations, AIM predicts an aligned spatial value map that encodes task-relevant interaction structure, enabling a control-oriented abstraction of future dynamics. Built on a pretrained
video generation model, AIM jointly models future observations and value maps within a shared mixture-of-
transformers architecture. It employs intent-causal
attention to route future information to the action branch exclusively through the value representation. We further propose a self-
distillation reinforcement learning stage that freezes the
video and value branches and optimizes only the action head using dense rewards derived from projected value-map responses together with sparse task-level signals. To support training and evaluation, we construct a simulation
dataset of 30K manipulation trajectories with synchronized multi-view observations, actions, and value-map annotations. Experiments on RoboTwin 2.0
benchmark show that AIM achieves a 94.0% average success rate, significantly outperforming prior unified world action baselines. Notably, the improvement is more pronounced in long-horizon and contact-sensitive manipulation tasks, demonstrating the effectiveness of explicit spatial-intent modeling as a bridge between visual world modeling and
robot control.
Read the full abstract ▾
All authors Liaoyuan Fan, Zetian Xu, Chen Cao, Wenyao Zhang, Mingqi Yuan, Jiayu Chen
Machine Learning · Cross-listed from cs.AI
MADQRL: Distributed Quantum Reinforcement Learning Framework for Multi-Agent Environments
Abhishek Sawaika, Samuel Yen-Chi Chen, Udaya Parampalli et al. (+1 more)
Reinforcement learning (RL) is one of the most practical ways to learn from real-life use-cases. Motivated from the cognitive methods used by humans makes it a widely acceptable strategy in the field of artificial intelligence. Most of the environments used for RL are often high-dimensional, and traditional RL
algorithms becomes computationally expensive and challenging to effectively learn from such systems. Recent advancements in practical demonstration of
quantum computing (QC) theories, such as compact encoding, enhanced representation and learning
algorithms, random sampling, or the inherent
stochastic nature of
quantum systems, have opened up new directions to tackle these challenges.
Quantum reinforcement learning (QRL) is seeking significant traction over the past few years. However, the current state of
quantum hardware is not enough to cater for such high-dimensional environments with complex multi-
agent setup. To tackle this issue, we propose a distributed framework for QRL where multiple
agents learn independently, distributing the load of joint training from individual machines. Our method works well for environments with disjoint sets of action and observation spaces, but can also be extended to other systems with reasonable approximations. We analyze the proposed method on cooperative-pong environment and our results indicate ~10% improvement from other distribution strategies, and ~5% improvement from classical models of policy representation.
Read the full abstract ▾
All authors Abhishek Sawaika, Samuel Yen-Chi Chen, Udaya Parampalli, Rajkumar Buyya
Machine Learning · Cross-listed from stat.ML
DDO-RM: Distribution-Level Policy Improvement after Reward Learning
Tiantian Zhang, Jierui Zuo, Michael Chen et al. (+1 more)
Recent theory suggests that reward-model-first methods can be more sample-efficient than direct policy fitting when the reward function is statistically simpler than the induced policy. We propose DDO-RM, a finite-candidate decision-optimization method that converts reward scores into an explicit target distribution. Unlike PPO-based RLHF or DPO, DDO-RM performs a KL-regularized mirror-descent update to project the policy toward a reward-improved distribution over a candidate set. Preliminary experiments on Pythia-410M show that DDO-RM outperforms DPO in pair accuracy (0.52 to 0.56) and mean margin (0.13 to 0.53). Our framework provides a principled connection between reward learning and mirror-descent policy improvement.
Read the full abstract ▾
All authors Tiantian Zhang, Jierui Zuo, Michael Chen, Wenping Wang
Machine Learning
Distributionally Robust K-Means Clustering
Vikrant Malik, Taylan Kargin and Babak Hassibi
K-means clustering is a workhorse of unsupervised learning, but it is notoriously brittle to outliers, distribution shifts, and limited sample sizes. Viewing k-means as Lloyd–Max quantization of the empirical distribution, we develop a distributionally robust variant that protects against such pathologies. We posit that the unknown population distribution lies within a Wasserstein-2 ball around the empirical distribution. In this setting, one seeks cluster centers that minimize the worst-case expected squared distance over this ambiguity set, leading to a minimax formulation. A tractable dual yields a soft-clustering scheme that replaces hard assignments with smoothly weighted ones. We propose an efficient block coordinate descent
algorithm with provable monotonic decrease and local linear convergence. Experiments on standard
benchmarks and large-scale synthetic data demonstrate substantial gains in outlier detection and robustness to noise.
Read the full abstract ▾
Machine Learning
Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning
Linjie Li, Huiyu Xiao, Jiarui Cao et al. (+2 more)
Class-incremental learning (CIL) aims to continuously accumulate knowledge from a stream of tasks and construct a unified classifier over all seen classes. Although pretrained models (PTMs) have shown promising performance in CIL, they still struggle with the
entanglement of multi-task subspaces, leading to catastrophic forgetting when task routing parameters are poorly calibrated or task-level representations are rigidly fixed. To address this issue, we propose a novel
Quantum-Gated Task-interaction Knowledge
Distillation (QKD) framework that leverages
quantum gating to guide inter-task knowledge transfer. Specifically, we introduce a
quantum-gated task modulation gating mechanism to model the relational dependencies among task
embedding, dynamically capturing the sample-to-task relevance for both joint training and inference across streaming tasks. Guided by the
quantum gating outputs, we perform task-interaction knowledge
distillation guided by these task-
embedding-level correlation weights from old to new adapters, enabling the model to bridge the representation gaps between independent task subspaces. Extensive experiments demonstrate that QKD effectively mitigates forgetting and achieves state-of-the-art performance.
Read the full abstract ▾
All authors Linjie Li, Huiyu Xiao, Jiarui Cao, Zhenyu Wu, Yang Ji
Machine Learning · Cross-listed from cs.DC
Record-Remix-Replay: Hierarchical GPU Kernel Optimization using Evolutionary Search
Daniel Nichols, Konstantinos Parasyris, Caetano Melone et al. (+3 more)
As high-performance computing and AI workloads become increasingly dependent on GPUs, maintaining high performance across rapidly evolving hardware generations has become a major challenge. Developers often spend months tuning scientific applications to fully exploit new architectures, navigating a complex optimization space that spans
algorithm design, source implementation, compiler flags and pass sequences, and kernel launch parameters. Existing approaches can effectively search parts of this space in isolation, such as launch configurations or compiler settings, but optimizing across the full space still requires substantial human expertise and iterative manual effort. In this paper, we present Record-Remix-Replay (R^3), a hierarchical optimization framework that combines LLM-driven evolutionary search,
Bayesian optimization, and record-replay compilation techniques to efficiently explore GPU kernel optimizations from source-level implementation choices down to compiler pass ordering and runtime configuration. By making candidate evaluation fast and scalable, our approach enables practical end-to-end search over optimization dimensions that are typically treated separately. We show that Record-Remix-Replay can optimize full scientific applications better than traditional approaches over kernel parameters and compiler flags, while also being nearly an order of magnitude faster than modern evolutionary search approaches.
Read the full abstract ▾
All authors Daniel Nichols, Konstantinos Parasyris, Caetano Melone, Tal Ben-Nun, Giorgis Georgakoudis, Harshitha Menon
Machine Learning · Cross-listed from cs.AI
Frugal Knowledge Graph Construction with Local LLMs: A Zero-Shot Pipeline, Self-Consistency and Wisdom of Artificial Crowds
Pierre Jourlin
This paper presents an empirical study of a multi-model zero-shot pipeline for knowledge graph construction and exploitation, executed entirely through local inference on consumer-grade hardware. We propose a reproducible evaluation framework integrating two external
benchmarks (DocRED, HotpotQA), WebQuestionsSP-style synthetic data, and the RAGAS evaluation framework in an automated pipeline. On 500 document-level relations, our system achieves an F1 of 0.70 $\pm$ 0.041 in zero-shot, compared to 0.80 for supervised DREEAM. Text-to-query achieves an accuracy of 0.80 $\pm$ 0.06 on 200 samples. Multi-hop
reasoning achieves an Exact Match (EM) of 0.46$\pm$0.04 on 500 HotpotQA questions, with a RAGAS faithfulness of 0.96 $\pm$ 0.04 on 50 samples. Beyond the pipeline, we study diversity mechanisms for difficult multi-hop
reasoning. On 181 questions unsolvable at zero temperature, self-consistency (k=5, T =0.7) recovers up to 23% EM with a single Mixture-of-Experts (MoE) model, but the cross-model oracle (3 architectures x 5 samples) reaches 46.4%. We highlight an agreement paradox: strong consensus among samples signals collective
hallucination rather than a reliable answer, echoing the work of Moussaïd et al. on the wisdom of crowds. Extending to the full pipeline (500 questions), self-consistency (k=3) raises EM from 0.46 to 0.48 $\pm$ 0.04. A confidence-routing cascade mechanism (Phi-4 $\rightarrow$ GPT-OSS, k=5) achieves an EM of 0.55 $\pm$ 0.04, the best result obtained, with 45.4% of questions rerouted. Finally, we show that V3
prompt engineering applied to other models does not reproduce the gains observed with Gemma-4, confirming the specific
prompt/model interaction. The entire system runs in $\sim$5 h on a single RTX 3090, without any training, for an estimated carbon footprint of 0.09 kg CO2 eq.
Read the full abstract ▾
Machine Learning · Cross-listed from math.CO
Geordie Williamson, Oded Yacobi and Paul Zinn-Justin
We present a new method for constructing Hadamard
matrices that combines
transformer neural networks with local search in the PatternBoost framework. Our approach is designed for extremely sparse combinatorial search problems and is particularly effective for Hadamard
matrices of Goethals–Seidel type, where
Fourier methods permit fast scoring and optimisation. For orders between 100 and 200, it produces large numbers of inequivalent Hadamard
matrices, and for larger orders, it succeeds where local search from random initialisation fails. The largest example found by our method has order 252. In addition to these new constructions, our experiments reveal that the
transformer can discover and exploit useful hidden
symmetry in the search space.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Efficient Transceiver Design for Aerial Image Transmission and Large-scale Scene Reconstruction
Zeyi Ren, Jialin Dong, Wei Zuo et al. (+4 more)
Large-scale three-dimensional (3D) scene reconstruction in low-altitude intelligent networks (LAIN) demands highly efficient wireless image transmission. However, existing schemes struggle to balance severe pilot overhead with the transmission accuracy required to maintain reconstruction fidelity. To strike a balance between efficiency and reliability, this paper proposes a novel deep learning-based end-to-end (E2E) transceiver design that integrates 3D Gaussian Splatting (3DGS) directly into the training process. By jointly optimizing the communication modules via the combined 3DGS rendering loss, our approach explicitly improves scene recovery quality. Furthermore, this task-driven framework enables the use of a sparse pilot scheme, significantly reducing transmission overhead while maintaining robust image recovery under low-altitude channel conditions. Extensive experiments on real-world aerial image
datasets demonstrate that the proposed E2E design significantly outperforms existing baselines, delivering superior transmission performance and accurate 3D scene reconstructions.
Read the full abstract ▾
All authors Zeyi Ren, Jialin Dong, Wei Zuo, Yikun Wang, Bingyang Cheng, Sheng Zhou, Zhisheng Niu
Machine Learning
Siyu Sun, Jing Ren, Zhaohe Liao et al. (+8 more)
Adapting decoder-only
multimodal large
language models (MLLMs) for unified
multimodal retrieval faces two structural gaps. First, existing methods rely on implicit pooling, which overloads the hidden state of a standard vocabulary
token (e.g., <EOS>) as the sequence-level representation, a mechanism never designed for information aggregation. Second, contrastive fine-tuning specifies what the
embedding should match but provides no
token-level guidance on how information should be compressed into it. We address both gaps with two complementary components. Architecturally, we introduce Bottleneck
Tokens (BToks), a small set of learnable
tokens that serve as a fixed-capacity explicit pooling mechanism. For training, we propose Generative Information Condensation: a next-
token prediction objective coupled with a Condensation Mask that severs the direct
attention path from target
tokens to query
tokens. All predictive signals are thereby forced through the BToks, converting the generative loss into dense,
token-level supervision for semantic compression. At inference time, only the input and BToks are processed in a single forward pass with negligible overhead over conventional last-
token pooling. On MMEB-V2 (78
datasets, 3 modalities, 9 meta-tasks), our approach achieves state-of-the-art among 2B-scale methods under comparable data conditions, attaining an Overall score of 59.0 (+3.6 over VLM2Vec-V2) with substantial gains on semantically demanding tasks (e.g., +12.6 on
Video-QA).
Read the full abstract ▾
All authors Siyu Sun, Jing Ren, Zhaohe Liao, Dongxiao Mao, Xiangyuan Ren, Yiyi Zhang, Haohua Zhao, Weixiong Lin, Jiang Shaohua, Liqing Zhang, Yuchao Zheng
Machine Learning
CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models
Linggang Kong, Lei Wu, Yunlong Zhang et al. (+4 more)
Despite the groundbreaking advancements made by large
language models (LLMs),
hallucination remains a critical bottleneck for their deployment in high-stakes domains. Existing classification-based methods mainly rely on static and passive signals from internal states, which often captures the noise and spurious correlations, while overlooking the underlying causal mechanisms. To address this limitation, we shift the paradigm from passive observation to active intervention by introducing CausalGaze, a novel
hallucination detection framework based on structural causal models (SCMs). CausalGaze models LLMs' internal states as dynamic causal graphs and employs counterfactual interventions to disentangle causal
reasoning paths from incidental noise, thereby enhancing model interpretability. Extensive experiments across four
datasets and three widely used LLMs demonstrate the effectiveness of CausalGaze, especially achieving 3.3% improvement in AUROC on the TruthfulQA
dataset compared to state-of-the-art baselines.
Read the full abstract ▾
All authors Linggang Kong, Lei Wu, Yunlong Zhang, Xiaofeng Zhong, Zhen Wang, Yongjie Wang, Yao Pan
Machine Learning · Cross-listed from cs.CV
Lightweight Low-Light Image Enhancement via Distribution-Normalizing Preprocessing and Depthwise U-Net
Shimon Murai, Teppei Kurita, Ryuta Satoh et al. (+1 more)
We present a lightweight two-stage framework for low-light image enhancement (LLIE) that achieves competitive perceptual quality with significantly fewer parameters than existing methods. Our approach combines frozen
algorithm-based preprocessing with a compact U-Net built entirely from depthwise-separable convolutions. The preprocessing normalizes the input distribution by providing complementary brightness-corrected views, enabling the trainable network to focus on residual color correction. Our method achieved 3rd place in the CVPR 2026 NTIRE Efficient Low-Light Image Enhancement Challenge. We further provide extended
benchmarks and ablations to demonstrate the general effectiveness of our methods.
Read the full abstract ▾
All authors Shimon Murai, Teppei Kurita, Ryuta Satoh, Yusuke Moriuchi
Machine Learning
A Faster Path to Continual Learning
Wei Li, Hangjie Yuan, Zixiang Zhao et al. (+3 more)
Continual Learning (CL) aims to train neural networks on a dynamic stream of tasks without forgetting previously learned knowledge. Among optimization-based approaches, C-Flat has emerged as a promising solution due to its plug-and-play nature and its ability to encourage uniformly low-loss regions for both new and old tasks. However, C-Flat requires three additional gradient computations per iteration, imposing substantial overhead on the optimization process. In this work, we propose C-Flat Turbo, a faster yet stronger optimizer that significantly reduces the training cost. We show that the gradients associated with first-order flatness contain direction-invariant components relative to the proxy-model gradients, enabling us to skip redundant gradient computations in the perturbed ascent steps. Moreover, we observe that these flatness-promoting gradients progressively stabilize across tasks, which motivates a linear scheduling strategy with an adaptive trigger to allocate larger turbo steps for later tasks. Experiments show that C-Flat Turbo is 1.0$\times$ to 1.25$\times$ faster than C-Flat across a wide range of CL methods, while achieving comparable or even improved accuracy.
Read the full abstract ▾
All authors Wei Li, Hangjie Yuan, Zixiang Zhao, Borui Kang, Ziwei Liu, Tao Feng
Machine Learning
Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?
Ziqian Zhong, Aashiq Muhamed, Mona T. Diab et al. (+2 more)
Mechanistic interpretability is often motivated for
alignment auditing, where a model's verbal explanations can be absent, incomplete, or misleading. Yet many evaluations do not control whether black-box prompting alone can recover the target behavior, so apparent gains from white-box tools may reflect elicitation rather than internal signal; we call this the elicitation confounder. We introduce Pando, a model-organism
benchmark that breaks this confound via an explanation axis: models are trained to produce either faithful explanations of the true rule, no explanation, or confident but unfaithful explanations of a disjoint distractor rule. Across 720 finetuned models implementing hidden decision-tree rules,
agents predict held-out model decisions from $10$ labeled query-response pairs, optionally augmented with one interpretability tool output. When explanations are faithful, black-box elicitation matches or exceeds all white-box methods; when explanations are absent or misleading, gradient-based attribution improves accuracy by 3-5 percentage points, and relevance patching, RelP, gives the largest gains, while logit lens, sparse autoencoders, and
circuit tracing provide no reliable benefit. Variance decomposition suggests gradients track decision computation, which fields causally drive the output, whereas other readouts are dominated by task representation, biases toward field identity and value. We release all models, code, and evaluation infrastructure.
Read the full abstract ▾
All authors Ziqian Zhong, Aashiq Muhamed, Mona T. Diab, Virginia Smith, Aditi Raghunathan
Machine Learning
Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR
Yuhang He, Haodong Wu, Siyi Liu et al. (+7 more)
Reinforcement Learning with Verifiable Rewards (RLVR) improves the
reasoning ability of Large
Language Models (LLMs), but sparse outcome rewards make
token-level credit assignment difficult. We study
token-level credit as a reward-conditioned shift from the behavior policy to a hindsight posterior. In autoregressive RLVR, this shift can be expressed through Conditional Mutual Information (CMI), which shows that
token entropy upper-bounds possible hindsight credit.
Entropy, however, indicates capacity rather than update direction, so we introduce the Four Quadrant Decomposition to separate updates by reward polarity and
token entropy. Controlled interventions show that these two factors jointly shape
token updates. Sustained
reasoning gains concentrate in signed high-
entropy quadrants, whereas low-
entropy updates saturate quickly. Based on this analysis, we propose Hindsight-Aware Policy Optimization (HAPO), a sign-preserving modification to GRPO that performs capacity-guided advantage reallocation. Experiments on mathematical
reasoning benchmarks in two model settings show that HAPO achieves competitive performance among
entropy-aware baselines.
Read the full abstract ▾
All authors Yuhang He, Haodong Wu, Siyi Liu, Hongyu Ge, Hange Zhou, Keyi Wu, Zhuo Zheng, Qihong Lin, Zixin Zhong, Yongqi Zhang
Machine Learning
RTMC: Step-Level Credit Assignment via Rollout Trees
Tao Wang, Suhang Zheng and Xiaoxiao Xu
Multi-step agentic reinforcement learning benefits from fine-grained credit assignment, yet existing approaches offer limited options: critic-free methods like GRPO assign a uniform advantage to every action in a trajectory, while learned value networks introduce notable overhead and can be fragile under sparse rewards. We observe that group rollouts targeting the same problem often traverse overlapping intermediate states, implicitly forming a tree whose branches diverge at successive decision points. Building on this insight, we introduce Rollout-Tree Monte Carlo (RTMC) advantage estimation, which aggregates return statistics across rollouts sharing a common state to produce per-step Q-values and advantages–without any learned critic. A state-action signature system compresses raw interaction histories into compact, comparable representations, making cross-rollout state matching tractable. On SWE-bench Verified, RTMC improves pass@1 by 3.2 percentage points over GRPO.
Read the full abstract ▾
Machine Learning
Worst-Case Optimal $\sqrt{\epsilon}$-Rate Stability of KL Divergence under Perturbations of Gaussian Distributions
Jialu Pan, Yufeng Zhang, Nan Hu et al. (+3 more)
We establish a stability bound for the Kullback-Leibler (KL) divergence when its Gaussian reference distribution is perturbed. Existing relaxed triangle inequalities of KL divergence between Gaussian distributions require all three distributions to be Gaussian, which limits their use in applications such as out-of-distribution detection with flow-based generative models. Let $\mathcal{N}_1$ and $\mathcal{N}_2$ be $d$-dimensional Gaussian distributions, and let $P$ be any $d$-dimensional distribution satisfying $\mathbb{E}_P[\|X\|^2]<\infty$ and $\mathrm{KL}(P\Vert \mathcal{N}_1)<\infty$. If $\mathrm{KL}(\mathcal{N}_1\Vert\mathcal{N}_2)\leq\epsilon$ for $0<\epsilon<1/12$, we give an upper bound of $\left|\mathrm{KL}(P\Vert\mathcal{N}_1)-\mathrm{KL}(P\Vert\mathcal{N}_2)\right|$. Under suitable uniform boundedness conditions, the bound is $ \frac{\sqrt{6d\epsilon}}{2}+K\sqrt{\epsilon}+o(\sqrt{\epsilon})$ as $\epsilon\rightarrow 0$ for fixed $d$, where $K$ depends on the parameters of $\mathcal{N}_1$ and $\mathcal{N}_2$, and on $\mathbb{E}_P[\|X\|]$ and $\mathbb{E}_P[\|X\|^2]$. Furthermore, we prove that the $\sqrt{\epsilon}$ dependence is worst-case optimal. The result extends stability guarantees restricted to Gaussian triples to comparisons involving an arbitrary distribution and two nearby Gaussian references. Experiments on synthetic distributions and latent representations from flow-based models support the predicted stability behavior.
Read the full abstract ▾
All authors Jialu Pan, Yufeng Zhang, Nan Hu, Zhenbang Chen, Ji Wang, Keqin Li
Machine Learning · Cross-listed from cs.AI
Min-$k$ Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics
Yuanhao Ding, Meimingwei Li, Esteban Garces Arias et al. (+3 more)
The quality of text generated by large
language models depends critically on the decoding sampling strategy. While mainstream methods such as Top-$k$, Top-$p$, and Min-$p$ achieve a balance between diversity and accuracy through probability-space truncation, they share an inherent limitation: extreme sensitivity to the temperature parameter. Recent logit-space approaches like Top-$n\sigma$ achieve temperature invariance but rely on global statistics that are susceptible to long-tail noise, failing to capture fine-grained confidence structures among top candidates. We propose \textbf{Min-$k$ Sampling}, a novel dynamic truncation strategy that analyzes the local shape of the sorted logit distribution to identify "semantic cliffs": sharp transitions from high-confidence core
tokens to uncertain long-tail
tokens. By computing a position-weighted relative decay rate, Min-$k$ dynamically determines truncation boundaries at each generation step. We formally prove that Min-$k$ achieves strict temperature invariance and empirically demonstrate its low sensitivity to hyperparameter choices. Experiments on multiple
reasoning benchmarks, creative writing tasks, and human evaluation show that Min-$k$ consistently improves text quality, maintaining robust performance even under extreme temperature settings where probability-based methods collapse. We make our code, models, and analysis tools publicly available.
Read the full abstract ▾
All authors Yuanhao Ding, Meimingwei Li, Esteban Garces Arias, Matthias Aßenmacher, Christian Heumann, Chongsheng Zhang
Machine Learning
K-Way Energy Probes for Metacognition Reduce to Softmax in Discriminative Predictive Coding Networks
Jon-Paul Cacioli
We present this as a negative result with an explanatory mechanism, not as a formal upper bound. Predictive coding networks (PCNs) admit a K-way energy probe in which each candidate class is fixed as a target, inference is run to settling, and the per-hypothesis settled energies are compared. The probe appears to read a richer signal source than softmax, since the per-hypothesis energy depends on the entire generative chain. We argue this appearance is misleading under the standard Pinchetti-style discriminative PC formulation. We present an approximate reduction showing that with target-clamped CE-energy training and effectively-feedforward latent dynamics, the K-way energy margin decomposes into a monotone function of the log-softmax margin plus a residual that is not trained to correlate with correctness. The decomposition predicts that the structural probe should track softmax from below. We test this across six conditions on CIFAR-10: extended deterministic training, direct measurement of latent movement during inference, a post-hoc decoder
fairness control on a backpropagation network, a matched-budget PC vs BP comparison, a five-point Langevin temperature sweep, and trajectory-integrated MCPC training. In every condition the probe sat below softmax. The gap was stable across training procedures within the discriminative PC family. Final-state and trajectory-integrated training produced probes whose AUROC_2 values differed by less than 10^-3 at deterministic evaluation. The empirical regime is small: single seed, 2.1M-parameter network, 1280 test images. We frame the result as a preprint inviting replication. We discuss conditions under which the decomposition does not apply (bidirectional PC, prospective configuration, generative PC, non-CE energy formulations) and directions for productive structural probing the analysis does not foreclose.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Panoptic Pairwise Distortion Graph
Muhammad Kamran Janjua, Abdul Wahab and Bahador Rashidi
In this work, we introduce a new perspective on comparative image assessment by representing an image pair as a structured composition of its regions. In contrast, existing methods focus on whole image analysis, while implicitly relying on region-level understanding. We extend the intra-image notion of a scene graph to inter-image, and propose a novel task of Distortion Graph (DG). DG treats paired images as a structured
topology grounded in regions, and represents dense degradation information such as distortion type, severity, comparison and quality score in a compact interpretable graph structure. To realize the task of learning a distortion graph, we contribute (i) a region-level
dataset, PandaSet, (ii) a
benchmark suite, PandaBench, with varying region-level difficulty, and (iii) an efficient architecture, Panda, to generate distortion graphs. We demonstrate that PandaBench poses a significant challenge for state-of-the-art
multimodal large
language models (MLLMs) as they fail to understand region-level degradations even when fed with explicit region cues. We show that training on PandaSet or prompting with DG elicits region-wise distortion understanding, opening a new direction for fine-grained, structured pairwise image assessment.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Sanity Checks for Agentic Data Science
Zachary T. Rewolinski, Austin V. Zane, Hao Huang et al. (+4 more)
Agentic data science (ADS) pipelines have grown rapidly in both capability and adoption, with systems such as OpenAI Codex now able to directly analyze
datasets and produce answers to statistical questions. However, these systems can reach falsely optimistic conclusions that are difficult for users to detect. To address this, we propose a pair of lightweight sanity checks grounded in the Predictability-Computability-Stability (PCS) framework for veridical data science. These checks use reasonable perturbations to screen whether an
agent can reliably distinguish signal from noise, acting as a falsifiability constraint that can expose affirmative conclusions as unsupported. Together, the two checks characterize the trustworthiness of an ADS output, e.g. whether it has found stable signal, is responding to noise, or is sensitive to incidental aspects of the input. We validate the approach on synthetic data with controlled signal-to-noise ratios, confirming that the sanity checks track ground-truth signal strength. We then demonstrate the checks on 11 real-world
datasets using OpenAI Codex, characterizing the trustworthiness of each conclusion and finding that in 6 of the
datasets an affirmative conclusion is not well-supported, even though a single ADS run may support one. We further analyze failure modes of ADS systems and find that ADS self-reported confidence is poorly calibrated to the empirical stability of its conclusions.
Read the full abstract ▾
All authors Zachary T. Rewolinski, Austin V. Zane, Hao Huang, Chandan Singh, Chenglong Wang, Jianfeng Gao, Bin Yu
Machine Learning
Flow-Controlled Scheduling for LLM Inference with Provable Stability Guarantees
Zhuolun Dong and Junyu Cao
Large
language models (LLMs) have been widely adopted due to their great performance across a wide range of applications. ChatGPT and Gemini now serve hundreds of millions of active users and handle billions of user requests per day, which puts optimizing LLM inference into the spotlight. A key challenge in LLM inference is that decode lengths are unknown. The
memory usage for each request grows with generated
tokens, which may lead to overflow and cause system instability. To address this concern, we propose a simple flow-control framework that controls the rate at which
prompts join the active set. We derive a necessary condition that any stable system must satisfy and establish sufficient conditions under which our
algorithm provably achieves stability. Experiments show that, compared to commonly used strategies in practice, our approach achieves higher
token and request throughput, lower average and tail latency, and more stable KV cache utilization.
Read the full abstract ▾
Machine Learning
Tracking High-order Evolutions via Cascading Low-rank Fitting
Zhao Song
Diffusion models have become the de facto standard for modern visual generation, including well-established frameworks such as latent
diffusion and flow matching. Recently, modeling high-order dynamics has emerged as a promising frontier in generative modeling. Rather than only learning the first-order velocity field that transports random noise to a target data distribution, these approaches simultaneously learn higher-order derivatives, such as acceleration and jerk, yielding a diverse family of higher-order
diffusion variants. To represent higher-order derivatives, naive approaches instantiate separate neural networks for each order, which scales the parameter space linearly with the derivative order. To overcome this computational bottleneck, we introduce cascading low-rank fitting, an ordinary differential equation inspired method that approximates successive derivatives by applying a shared base function augmented with sequentially accumulated low-rank components. Theoretically, we analyze the rank dynamics of these successive
matrix differences. We prove that if the initial difference is linearly decomposable, the generic ranks of high-order derivatives are guaranteed to be monotonically non-increasing. Conversely, we demonstrate that without this structural assumption, the General Leibniz Rule allows ranks to strictly increase. Furthermore, we establish that under specific conditions, the sequence of derivative ranks can be designed to form any arbitrary permutation. Finally, we present a straightforward
algorithm to efficiently compute the proposed cascading low-rank fitting.
Read the full abstract ▾