Machine Learning
$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space
Peihao Wang, Ruisi Cai, Zhen Wang et al. (+4 more)
Scaling inference-time compute for Large
Language Models (LLMs) has unlocked unprecedented
reasoning capabilities. However, existing inference-time scaling methods typically rely on inefficient and suboptimal discrete search
algorithms or trial-and-error prompting to improve the online policy. In this paper, we propose $\nabla$-Reasoner, an iterative generation framework that integrates differentiable optimization over
token logits into the decoding loop to refine the policy on the fly. Our core component, Differentiable Textual Optimization (DTO), leverages gradient signals from both the LLM's likelihood and a reward model to refine textual representations. $\nabla$-Reasoner further incorporates rejection sampling and acceleration design to robustify and speed up decoding. Theoretically, we show that performing inference-time gradient descent in the sample space to maximize reward is dual to aligning an LLM policy via KL-regularized reinforcement learning. Empirically, $\nabla$-Reasoner achieves over 20% accuracy improvement on a challenging mathematical
reasoning benchmark, while reducing number of model calls by approximately 10-40% compared to strong baselines. Overall, our work introduces a paradigm shift from zeroth-order search to first-order optimization at test time, offering a cost-effective path to amplify LLM
reasoning.
Read the full abstract ▾
All authors Peihao Wang, Ruisi Cai, Zhen Wang, Hongyuan Mei, Qiang Liu, Pan Li, Zhangyang Wang
Machine Learning · Cross-listed from cs.CV
Person Detection and Tracking from an Overhead Crane LiDAR
Nilusha Jayawickrama, Henrik Toikka and Risto Ojala
This paper investigates person detection and tracking in an industrial indoor workspace using a
LiDAR mounted on an overhead crane. The overhead viewpoint introduces a strong domain shift from common vehicle-centric
LiDAR benchmarks, and limited availability of suitable public training data. Henceforth, we curate a site-specific overhead
LiDAR dataset with 3D human bounding-box annotations and adapt selected candidate 3D detectors under a unified training and evaluation protocol. We further integrate lightweight tracking-by-detection using AB3DMOT and SimpleTrack to maintain person identities over time. Detection performance is reported with distance-sliced evaluation to quantify the practical operating envelope of the sensing setup. The best adapted detector configurations achieve average precision (AP) up to 0.84 within a 5.0 m horizontal radius, increasing to 0.97 at 1.0 m, with VoxelNeXt and SECOND emerging as the most reliable backbones across this range. The acquired results contribute in bridging the domain gap between standard driving
datasets and overhead sensing for person detection and tracking. We also report latency measurements, highlighting practical real-time feasibility. Finally, we release our
dataset and implementations in GitHub to support further research
Read the full abstract ▾
Machine Learning
Semantic Communication-Enhanced Split Federated Learning for Vehicular Networks: Architecture, Challenges, and Case Study
Lu Yu, Zheng Chang and Ying-Chang Liang
Vehicular edge intelligence (VEI) is vital for future intelligent transportation systems. However, traditional centralized learning in dynamic vehicular networks faces significant communication overhead and
privacy risks. Split
federated learning (SFL) offers a distributed solution but is often hindered by substantial communication bottlenecks from transmitting high-dimensional intermediate features and can present label
privacy concerns. Semantic communication offers a transformative approach to alleviate these communication challenges in SFL by focusing on transmitting only task-relevant information. This paper leverages the advantages of semantic communication in the design of SFL, and presents a case study the semantic communication-enhanced U-Shaped split
federated learning (SC-USFL) framework that inherently enhances label
privacy by localizing sensitive computations with reduced overhead. It features a dedicated semantic communication module (SCM), with pre-trained and parameter-frozen encoding/decoding units, to efficiently compress and transmit only the task-relevant semantic information over the critical uplink path from vehicular users to the edge server (ES). Furthermore, a network status monitor (NSM) module enables adaptive adjustment of the semantic compression rate in real-time response to fluctuating wireless channel conditions. The SC-USFL framework demonstrates a promising approach for efficiently balancing communication load, preserving
privacy, and maintaining learning performance in resource-constrained vehicular environments. Finally, this paper highlights key open research directions to further advance the synergy between semantic communication and SFL in the vehicular network.
Read the full abstract ▾
Machine Learning
BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning
Yuan Li, Bo Wang, Yufei Gao et al. (+4 more)
Proximal constraints are fundamental to the stability of the Large
Language Model reinforcement learning. While the canonical clipping mechanism in PPO serves as an efficient surrogate for trust regions, we identify a critical bottleneck: fixed bounds strictly constrain the upward update margin of low-probability actions, disproportionately suppressing high-advantage tail strategies and inducing rapid
entropy collapse. To address this, we introduce Band-constrained Policy Optimization (BandPO). BandPO replaces canonical clipping with Band, a unified theoretical operator that projects trust regions defined by f-divergences into dynamic, probability-aware clipping intervals. Theoretical analysis confirms that Band effectively resolves this exploration bottleneck. We formulate this mapping as a convex optimization problem, guaranteeing a globally optimal numerical solution while deriving closed-form solutions for specific divergences. Extensive experiments across diverse models and
datasets demonstrate that BandPO consistently outperforms canonical clipping and Clip-Higher, while robustly mitigating
entropy collapse.
Read the full abstract ▾
All authors Yuan Li, Bo Wang, Yufei Gao, Yuqian Yao, Xinyuan Wang, Zhangyue Yin, Xipeng Qiu
Machine Learning
EVMbench: Evaluating AI Agents on Smart Contract Security
Justin Wang, Andreas Bigger, Xiaohai Xu et al. (+5 more)
Smart contracts on public blockchains now manage large amounts of value, and vulnerabilities in these systems can lead to substantial losses. As AI
agents become more capable at reading, writing, and running code, it is natural to ask how well they can already navigate this landscape, both in ways that improve security and in ways that might increase risk. We introduce EVMbench, an evaluation that measures the ability of
agents to detect, patch, and exploit smart contract vulnerabilities. EVMbench draws on 117 curated vulnerabilities from 40 repositories and, in the most realistic setting, uses programmatic grading based on tests and blockchain state under a local Ethereum execution environment. We evaluate a range of frontier
agents and find that they are capable of discovering and exploiting vulnerabilities end-to-end against live blockchain instances. We release code, tasks, and tooling to support continued measurement of these capabilities and future work on security.
Read the full abstract ▾
All authors Justin Wang, Andreas Bigger, Xiaohai Xu, Justin W. Lin, Andy Applebaum, Tejal Patwardhan, Alpin Yukseloglu, Olivia Watkins
Machine Learning · Cross-listed from cs.RO
VPWEM: Non-Markovian Visuomotor Policy with Working and Episodic Memory
Yuheng Lei, Zhixuan Liang, Hongyuan Zhang et al. (+1 more)
Imitation learning from human demonstrations has achieved significant success in robotic control, yet most visuomotor policies still condition on single-step observations or short-context histories, making them struggle with non-Markovian tasks that require long-term
memory. Simply enlarging the context window incurs substantial computational and
memory costs and encourages overfitting to spurious correlations, leading to catastrophic failures under distribution shift and violating real-time constraints in robotic systems. By contrast, humans can compress important past experiences into long-term
memories and exploit them to solve tasks throughout their lifetime. In this paper, we propose VPWEM, a non-Markovian visuomotor policy equipped with working and episodic
memories. VPWEM retains a sliding window of recent observation
embeddings as short-term working
memory, and introduces a
Transformer-based contextual
memory compressor that recursively converts out-of-window observations into a fixed number of episodic
memory embeddings. The compressor uses self-
attention over a cache of past summary
embeddings and cross-
attention over a cache of historical observations, and is trained jointly with the policy. We instantiate VPWEM on
diffusion policies to exploit both short-term and episode-wide information for action generation with nearly constant
memory and computation per step. Experiments demonstrate that VPWEM outperforms state-of-the-art baselines including
diffusion policies and
vision-
language-action (VLA) models by more than 20% on the
memory-intensive manipulation tasks in MIKASA and achieves an average 5% improvement on the mobile manipulation
benchmark MoMaRT. Code is available at https://github.com/HarryLui98/code_vpwem.
Read the full abstract ▾
All authors Yuheng Lei, Zhixuan Liang, Hongyuan Zhang, Ping Luo
Machine Learning
U-Parking: Distributed UWB-Assisted Autonomous Parking System with Robust Localization and Intelligent Planning
Yiang Wu, Qiong Wu, Pingyi Fan et al. (+4 more)
This demonstration presents U-Parking, a distributed Ultra-Wideband (UWB)-assisted autonomous parking system. By integrating Large
Language Models (LLMs)-assisted planning with robust fusion localization and trajectory tracking, it enables reliable automated parking in challenging indoor environments, as validated through real-vehicle demonstrations.
Read the full abstract ▾
All authors Yiang Wu, Qiong Wu, Pingyi Fan, Kezhi Wang, Wen Chen, Guoqiang Mao, Khaled B. Letaief
Machine Learning · Cross-listed from stat.ML
How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?
Kuo-Wei Lai, Guanghui Wang, Molei Tao et al. (+1 more)
Overparameterized ML models, including neural networks, typically induce underdetermined training objectives with multiple global minima. The implicit bias refers to the limiting global minimum that is attained by a common optimization
algorithm, such as gradient descent (GD). In this paper, we characterize the implicit bias of GD for training a shallow ReLU model with the squared loss on high-dimensional random features. Prior work (Vardi and Shamir, 2021) showed that the implicit bias does not exist in the worst-case, or corresponds exactly to the minimum-$\ell_2$-norm interpolating solution under exactly orthogonal data (Boursier et al., 2022). Our work interpolates between these two extremes and shows that, for sufficiently high-dimensional random data, the implicit bias approximates the minimum-$\ell_2$-norm solution with high probability with a gap on the order $\Theta(\sqrt{n/||\lambda||_1})$, where $n$ is the number of training examples and $\lambda$ denotes the spectrum of the data covariance
matrix. Our results are obtained through a novel primal-dual analysis that carefully tracks the
evolution of predictions, data-span coefficients, as well as their interactions, and show that the ReLU activation pattern quickly stabilizes with high probability over random data.
Read the full abstract ▾
All authors Kuo-Wei Lai, Guanghui Wang, Molei Tao, Vidya Muthukumar
Machine Learning
Min Tan, Junchao Ma, Yinfu Feng et al. (+6 more)
Multimodal Federated Learning (MFL) enables clients with heterogeneous data modalities to collaboratively train models without sharing raw data, offering a
privacy-preserving framework that leverages complementary cross-modal information. However, existing methods often overlook personalized client performance and struggle with modality/task discrepancies, as well as model heterogeneity. To address these challenges, we propose FedAFD, a unified MFL framework that enhances client and server learning. On the client side, we introduce a bi-level
adversarial alignment strategy to align local and global representations within and across modalities, mitigating modality and task gaps. We further design a granularity-aware fusion module to integrate global knowledge into the personalized features adaptively. On the server side, to handle model heterogeneity, we propose a similarity-guided ensemble
distillation mechanism that aggregates client representations on shared public data based on feature similarity and distills the fused knowledge into the global model. Extensive experiments conducted under both IID and non-IID settings demonstrate that FedAFD achieves superior performance and efficiency for both the client and the server.
Read the full abstract ▾
All authors Min Tan, Junchao Ma, Yinfu Feng, Jiajun Ding, Wenwen Pan, Tingting Han, Qian Zheng, Zhenzhong Kuang, Zhou Yu
Machine Learning
Differential Privacy in Two-Layer Networks: How DP-SGD Harms Fairness and Robustness
Ruichen Xu and Kexin Chen
Differentially private learning is essential for training models on sensitive data, but empirical studies consistently show that it can degrade performance, introduce
fairness issues like disparate impact, and reduce
adversarial robustness. The theoretical underpinnings of these phenomena in modern, non-convex neural networks remain largely unexplored. This paper introduces a unified feature-centric framework to analyze the feature learning dynamics of differentially private
stochastic gradient descent (DP-SGD) in two-layer ReLU convolutional neural networks. Our analysis establishes test loss bounds governed by a crucial metric: the feature-to-noise ratio (FNR). We demonstrate that the noise required for
privacy leads to suboptimal feature learning, and specifically show that: 1) imbalanced FNRs across classes and subpopulations cause disparate impact; 2) even in the same class, noise has a greater negative impact on semantically long-tailed data; and 3) noise injection exacerbates vulnerability to
adversarial attacks. Furthermore, our analysis reveals that the popular paradigm of public pre-training and private fine-tuning does not guarantee improvement, particularly under significant feature distribution shifts between
datasets. Experiments on synthetic and real-world data corroborate our theoretical findings.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Interpretable Pre-Release Baseball Pitch Type Anticipation from Broadcast 3D Kinematics
Jerrin Bright, Michelle Lu and John Zelek
How much can a pitcher's body reveal about the upcoming pitch? We study this question at scale by classifying eight pitch types from
monocular 3D pose sequences, without access to ball-flight data. Our pipeline chains a
diffusion-based 3D pose backbone with automatic pitching-event detection, groundtruth-validated biomechanical feature extraction, and gradient-boosted classification over 229 kinematic features. Evaluated on 119,561 professional pitches, the largest such
benchmark to date, we achieve 80.4% accuracy using body kinematics alone. A systematic importance analysis reveals that upper-body mechanics contribute 64.9% of the predictive signal versus 35.1% for the lower body, with wrist position (14.8%) and trunk lateral tilt emerging as the most informative joint group and biomechanical feature, respectively. We further show that grip-defined variants (four-seam vs.\ two-seam fastball) are not separable from pose, establishing an empirical ceiling near 80% and delineating where kinematic information ends and ball-flight information begins.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Causally Robust Reward Learning from Reason-Augmented Preference Feedback
Minjune Hwang, Yigit Korkmaz, Daniel Seita et al. (+1 more)
Preference-based reward learning is widely used for shaping
agent behavior to match a user's preference, yet its sparse binary feedback makes it especially vulnerable to causal confusion. The learned reward often latches onto spurious features that merely co-occur with preferred trajectories during training, collapsing when those correlations disappear or reverse at test time. We introduce ReCouPLe, a lightweight framework that uses natural
language rationales to provide the missing causal signal. Each rationale is treated as a guiding projection axis in an
embedding space, training the model to score trajectories based on features aligned with that axis while de-emphasizing context that is unrelated to the stated reason. Because the same rationales (e.g., "avoids collisions", "completes the task faster") can appear across multiple tasks, ReCouPLe naturally reuses the same causal direction whenever tasks share semantics, and transfers preference knowledge to novel tasks without extra data or
language-model fine-tuning. Our learned reward model can ground preferences on the articulated reason, aligning better with user intent and generalizing beyond spurious features. ReCouPLe outperforms baselines by up to 1.5x in reward accuracy under distribution shifts, and 2x in downstream policy performance in novel tasks. We have released our code at https://github.com/mj-hwang/ReCouPLe
Read the full abstract ▾
All authors Minjune Hwang, Yigit Korkmaz, Daniel Seita, Erdem B{\i}y{\i}k
Machine Learning · Cross-listed from cs.CR
Osmosis Distillation: Model Hijacking with the Fewest Samples
Yuchen Shi, Huajie Chen, Heng Xu et al. (+6 more)
Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources. Meanwhile,
dataset distillation has emerged to synthesize a compact
dataset that preserves critical information from the original large
dataset. Therefore, a combination of transfer learning and
dataset distillation offers promising performance in evaluations. However, a non-negligible security threat remains undiscovered in transfer learning using synthetic
datasets generated by
dataset distillation methods, where an adversary can perform a model hijacking attack with only a few poisoned samples in the synthetic
dataset. To reveal this threat, we propose Osmosis
Distillation (OD) attack, a novel model hijacking strategy that targets deep learning models using the fewest samples. Comprehensive evaluations on various
datasets demonstrate that the OD attack attains high attack success rates in hidden tasks while preserving high model utility in original tasks. Furthermore, the distilled osmosis set enables model hijacking across diverse model architectures, allowing model hijacking in transfer learning with considerable attack performance and model utility. We argue that awareness of using third-party synthetic
datasets in transfer learning must be raised.
Read the full abstract ▾
All authors Yuchen Shi, Huajie Chen, Heng Xu, Zhiquan Liu, Jialiang Shen, Chi Liu, Shuai Zhou, Tianqing Zhu, Wanlei Zhou
Machine Learning
Why Is RLHF Alignment Shallow? A Gradient Analysis
Robin Young
Why is safety
alignment in LLMs shallow? We prove that gradient-based
alignment inherently concentrates on positions where harm is decided and vanishes beyond. Using a martingale decomposition of sequence-level harm, we derive an exact characterization of
alignment gradients. The gradient at position $t$ equals the covariance between the conditional expected harm and the score function. This implies that positions beyond the harm horizon where the output's harmfulness is already determined receive zero gradient signal during training. This explains empirical observations that KL divergence between aligned and base models concentrates on early
tokens. Consequently, standard
alignment objectives cannot produce deep
alignment, regardless of optimization quality. We introduce the concept of harm information $I_t$, which quantifies each position's influence on harm, and prove that
equilibrium KL divergence tracks this quantity. Finally, we derive an objective based on recovery penalties that creates gradient signal at all positions, providing theoretical grounding for empirically successful data augmentation techniques.
Read the full abstract ▾
Machine Learning
Missingness Bias Calibration in Feature Attribution Explanations
Shailesh Sridhar, Anton Xue and Eric Wong
Popular explanation methods often produce unreliable feature importance scores due to missingness bias, a systematic distortion that arises when models are probed with ablated, out-of-distribution inputs. Existing solutions treat this as a deep representational flaw that requires expensive retraining or architectural modifications. In this work, we challenge this assumption and show that missingness bias can be effectively treated as a superficial artifact of the model's output space. We introduce MCal, a lightweight post-hoc method that corrects this bias by fine-tuning a simple linear head on the outputs of a frozen base model. Surprisingly, we find this simple correction consistently reduces missingness bias and is competitive with, or even outperforms, prior heavyweight approaches across diverse medical
benchmarks spanning
vision,
language, and tabular domains.
Read the full abstract ▾
Machine Learning
Multilevel Training for Kolmogorov Arnold Networks
Ben S. Southworth, Jonas A. Actor, Graham Harper et al. (+1 more)
Algorithmic speedup of training common neural architectures is made difficult by the lack of structure guaranteed by the function compositions inherent to such networks. In contrast to multilayer perceptrons (MLPs), Kolmogorov-Arnold networks (KANs) provide more structure by expanding learned activations in a specified basis. This paper exploits this structure to develop practical
algorithms and theoretical insights, yielding training speedup via multilevel training for KANs. To do so, we first establish an equivalence between KANs with spline basis functions and multichannel MLPs with power ReLU activations through a linear change of basis. We then analyze how this change of basis affects the geometry of gradient-based optimization with respect to spline
knots. The KANs change-of-basis motivates a multilevel training approach, where we train a sequence of KANs naturally defined through a uniform refinement of spline
knots with analytic
geometric interpolation operators between models. The interpolation scheme enables a “properly nested hierarchy” of architectures, ensuring that interpolation to a fine model preserves the progress made on coarse models, while the compact support of spline basis functions ensures complementary optimization on subsequent levels. Numerical experiments demonstrate that our multilevel training approach can achieve orders of magnitude improvement in accuracy over conventional methods to train comparable KANs or MLPs, particularly for physics informed neural networks. Finally, this work demonstrates how principled design of neural networks can lead to exploitable structure, and in this case, multilevel
algorithms that can dramatically improve training performance.
Read the full abstract ▾
All authors Ben S. Southworth, Jonas A. Actor, Graham Harper, Eric C. Cyr
Machine Learning · Cross-listed from cs.CV
Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning
Rui Zhao, Bin Shi, Kai Sun et al. (+1 more)
Partial label learning is a prominent weakly supervised classification task, where each training instance is ambiguously labeled with a set of candidate labels. In real-world scenarios, candidate labels are often influenced by instance features, leading to the emergence of instance-dependent PLL (ID-PLL), a setting that more accurately reflects this relationship. A significant challenge in ID-PLL is instance
entanglement, where instances from similar classes share overlapping features and candidate labels, resulting in increased class confusion. To address this issue, we propose a novel Class-specific Augmentation based Disentanglement (CAD) framework, which tackles instance
entanglement by both intra- and inter-class regulations. For intra-class regulation, CAD amplifies class-specific features to generate class-wise augmentations and aligns same-class augmentations across instances. For inter-class regulation, CAD introduces a weighted penalty loss function that applies stronger penalties to more ambiguous labels, encouraging larger inter-class distances. By jointly applying intra- and inter-class regulations, CAD improves the clarity of class boundaries and reduces class confusion caused by
entanglement. Extensive experimental results demonstrate the effectiveness of CAD in mitigating the
entanglement problem and enhancing ID-PLL performance. The code is available at https://github.com/RyanZhaoIc/CAD.git.
Read the full abstract ▾
All authors Rui Zhao, Bin Shi, Kai Sun, Bo Dong
Machine Learning · Cross-listed from cs.RO
On the Strengths and Weaknesses of Data for Open-set Embodied Assistance
Pradyumna Tambwekar, Andrew Silva, Deepak Gopinath et al. (+3 more)
Embodied foundation models are increasingly performant in real-world domains such as robotics or autonomous driving. These models are often deployed in interactive or assistive settings, where it is important that these assistive models generalize to new users and new tasks. Diverse interactive data generation offers a promising avenue for providing data-efficient generalization capabilities for interactive
embodied foundation models. In this paper, we investigate the generalization capabilities of a
multimodal foundation model fine-tuned on diverse interactive assistance data in a synthetic domain. We explore generalization along two axes: a) assistance with unseen categories of user behavior and b) providing guidance in new configurations not encountered during training. We study a broad capability called Open-Set Corrective Assistance, in which the model needs to inspect lengthy user behavior and provide assistance through either corrective actions or
language-based feedback. This task remains unsolved in prior work, which typically assumes closed corrective categories or relies on external planners, making it a challenging testbed for evaluating the limits of assistive data. To support this task, we generate synthetic assistive
datasets in Overcooked and fine-tune a LLaMA-based model to evaluate generalization to novel tasks and user behaviors. Our approach provides key insights into the nature of assistive
datasets required to enable open-set assistive intelligence. In particular, we show that performant models benefit from
datasets that cover different aspects of assistance, including
multimodal grounding, defect inference, and exposure to diverse scenarios.
Read the full abstract ▾
All authors Pradyumna Tambwekar, Andrew Silva, Deepak Gopinath, Jonathan DeCastro, Xiongyi Cui, Guy Rosman
Machine Learning · Cross-listed from cs.CG
Quadratic polarity and polar Fenchel-Young divergences from the canonical Legendre polarity
Frank Nielsen, Basile Plus-Gourdon and Mahito Sugiyama
Polarity is a fundamental reciprocal duality of $n$-dimensional projective geometry which associates to points polar hyperplanes, and more generally $k$-dimensional convex bodies to polar $(n-1-k)$-dimensional convex bodies. It is well-known that the Legendre-Fenchel transformation of functions can be interpreted from the polarity viewpoint of their graphs using an extra dimension. In this paper, we first show that generic polarities induced by quadratic polarity functionals can be expressed either as deformed Legendre polarity or as the Legendre polarity of deformed convex bodies, and be efficiently manipulated using linear
algebra on $(n+2)\times (n+2)$
matrices operating on homogeneous coordinates. Second, we define polar divergences using the Legendre polarity and show that they generalize the Fenchel-Young divergence or equivalent Bregman divergence. This polarity study brings new understanding of the core reference duality in information geometry. Last, we show that the total Bregman divergences can be considered as a total polar Fenchel-Young divergence from which we newly exhibit the reference duality using dual polar conformal factors.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SD
WhisperAlign: Word-Boundary-Aware ASR and WhisperX-Anchored Pyannote Diarization for Long-Form Bengali Speech
Aurchi Chowdhury, Rubaiyat -E-Zaman and Sk. Ashrafuzzaman Nafees
This paper presents our solution for the DL Sprint 4.0, addressing the dual challenges of Bengali Long-Form
Speech Recognition (Task 1) and Speaker Diarization (Task 2). Processing long-form, multi-speaker Bengali audio introduces significant hurdles in voice activity detection, overlapping
speech, and context preservation. To solve the long-form transcription challenge, we implemented a robust audio chunking strategy utilizing whisper-timestamped, allowing us to feed precise, context-aware segments into our fine-tuned acoustic model for high-accuracy transcription. For the diarization task, we developed an integrated pipeline leveraging pyannote.audio and WhisperX. A key contribution of our approach is the domain-specific fine-tuning of the Pyannote
segmentation model on the competition
dataset. This adaptation allowed the model to better capture the nuances of Bengali conversational dynamics and accurately resolve complex, overlapping speaker boundaries. Our methodology demonstrates that applying intelligent timestamped chunking to ASR and targeted
segmentation fine-tuning to diarization significantly drives down Word Error Rate (WER) and Diarization Error Rate (DER), in low-resource settings.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability
Tongtong Liang, Esha Singh, Rahul Parhi et al. (+2 more)
Gradient descent on overparameterized neural networks typically operates at the Edge of Stability (EoS), where the largest Hessian
eigenvalue hovers around a step-size-dependent threshold. We study how sparse connectivity changes generalization below this threshold in two-layer ReLU networks. Prior results have shown that for fully-connected networks (FCNs), generalization guarantees in this regime degrade and become vacuous on high-dimensional spherical inputs. Our analysis reveals that sparse connectivity fundamentally alters this picture. Under sparse connectivity, the network processes a collection of low-dimensional patches rather than the full input vector, so the effective constraint imposed by the stability condition is governed by the geometry of the training patch collection. We prove that when the receptive fields are small relative to the ambient dimension, the effective constraint yields non-vacuous generalization bounds in precisely the spherical regime where FCNs provably fail. The same framework also reveals a contrasting failure mode: if the patch collection lacks
geometric structure, the constraint becomes unable to prevent overfitting. We corroborate this theory by analyzing the patch geometry of natural images, showing that standard convolutional designs produce patch multiset with low-dimensional structure that facilitates generalization. This provides a principled explanation for the generalization advantage of convolutional networks. Thus, our analysis yields a unified framework that identifies how architecture, data geometry, and gradient descent jointly govern generalization performance.
Read the full abstract ▾
All authors Tongtong Liang, Esha Singh, Rahul Parhi, Alexander Cloninger, Yu-Xiang Wang
Machine Learning · Cross-listed from cs.CV
Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation
Boyu Han, Qianqian Xu, Shilong Bao et al. (+4 more)
The limited understanding capacity of the visual encoder in Contrastive
Language-Image Pre-training (CLIP) has become a key bottleneck for downstream performance. This capacity includes both Discriminative Ability (D-Ability), which reflects class separability, and Detail Perceptual Ability (P-Ability), which focuses on fine-grained visual cues. Recent solutions use
diffusion models to enhance representations by conditioning image reconstruction on CLIP visual
tokens. We argue that such paradigms may compromise D-Ability and therefore fail to effectively address CLIP's representation limitations. To address this, we integrate contrastive signals into
diffusion-based reconstruction to pursue more comprehensive visual representations. We begin with a straightforward design that augments the
diffusion process with contrastive learning on input images. However, empirical results show that the naive combination suffers from gradient conflict and yields suboptimal performance. To balance the optimization, we introduce the
Diffusion Contrastive Reconstruction (DCR), which unifies the learning objective. The key idea is to inject contrastive signals derived from each reconstructed image, rather than from the original input, into the
diffusion process. Our theoretical analysis shows that the DCR loss can jointly optimize D-Ability and P-Ability. Extensive experiments across various
benchmarks and multi-modal large
language models validate the effectiveness of our method. The code is available at https://github.com/boyuh/DCR.
Read the full abstract ▾
All authors Boyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang, Ruochen Cui, Xilin Zhao, Qingming Huang
Machine Learning
Diffusion Policy through Conditional Proximal Policy Optimization
Ben Liu, Shunpeng Yang and Hua Chen
Reinforcement learning (RL) has been extensively employed in a wide range of decision-making problems, such as games and robotics. Recently,
diffusion policies have shown strong potential in modeling multi-modal behaviors, enabling more diverse and flexible action generation compared to the conventional Gaussian policy. Despite various attempts to combine RL with
diffusion, a key challenge is the difficulty of computing action log-likelihood under the
diffusion model. This greatly hinders the direct application of
diffusion policies in on-policy reinforcement learning. Most existing methods calculate or approximate the log-likelihood through the entire denoising process in the
diffusion model, which can be
memory- and computationally inefficient. To overcome this challenge, we propose a novel and efficient method to train a
diffusion policy in an on-policy setting that requires only evaluating a simple Gaussian probability. This is achieved by aligning the policy iteration with the
diffusion process, which is a distinct paradigm compared to previous work. Moreover, our formulation can naturally handle
entropy regularization, which is often difficult to incorporate into
diffusion policies. Experiments demonstrate that the proposed method produces
multimodal policy behaviors and achieves superior performance on a variety of
benchmark tasks in both IsaacLab and MuJoCo Playground.
Read the full abstract ▾
Machine Learning
Distributional Equivalence in Linear Non-Gaussian Latent-Variable Cyclic Causal Models: Characterization and Learning
Haoyue Dai, Immanuel Albrecht, Peter Spirtes et al. (+1 more)
Causal discovery with latent variables is a fundamental task. Yet most existing methods rely on strong structural assumptions, such as enforcing specific indicator patterns for latents or restricting how they can interact with others. We argue that a core obstacle to a general, structural-assumption-free approach is the lack of an equivalence characterization: without knowing what can be identified, one generally cannot design methods for how to identify it. In this work, we aim to close this gap for linear non-Gaussian models. We establish the graphical criterion for when two graphs with arbitrary latent structure and cycles are distributionally equivalent, that is, they induce the same observed distribution set. Key to our approach is a new tool, edge rank constraints, which fills a missing piece in the toolbox for latent-variable causal discovery in even broader settings. We further provide a procedure to traverse the whole equivalence class and develop an
algorithm to recover models from data up to such equivalence. To our knowledge, this is the first equivalence characterization with latent variables in any parametric setting without structural assumptions, and hence the first structural-assumption-free discovery method. Code and an interactive demo are available at https://equiv.cc.
Read the full abstract ▾
All authors Haoyue Dai, Immanuel Albrecht, Peter Spirtes, Kun Zhang
Machine Learning
Distributional Reinforcement Learning with Information Bottleneck for Uncertainty-Aware DRAM Equalization
Muhammad Usama and Dong Eui Chang
Equalizer parameter optimization is critical for signal integrity in high-speed
memory systems operating at multi-gigabit data rates. However, existing methods suffer from computationally expensive eye diagram evaluation, optimization of expected rather than worst-case performance, and absence of uncertainty quantification for deployment decisions. In this paper, we propose a distributional risk-sensitive reinforcement learning framework integrating Information Bottleneck latent representations with Conditional Value-at-Risk optimization. We introduce rate-distortion optimal signal compression achieving 51 times speedup over eye diagrams while quantifying epistemic uncertainty through Monte Carlo dropout. Distributional reinforcement learning with
quantile regression enables explicit worst-case optimization, while PAC-
Bayesian regularization certifies generalization bounds. Experimental validation on 2.4 million waveforms from eight
memory units demonstrated mean improvements of 37.1% and 41.5% for 4-tap and 8-tap equalizer configurations with worst-case guarantees of 33.8% and 38.2%, representing 80.7% and 89.1% improvements over Q-learning baselines. The framework achieved 62.5% high-reliability classification eliminating manual validation for most configurations. These results suggest the proposed framework provides a practical solution for production-scale equalizer optimization with certified worst-case guarantees.
Read the full abstract ▾
Machine Learning
ConTSG-Bench: A Unified Benchmark for Conditional Time Series Generation
Shaocheng Lan, Shuqi Gu, Zhangzhi Xiong et al. (+1 more)
Conditional time series generation plays a critical role in addressing data scarcity and enabling causal analysis in real-world applications. Despite its increasing importance, the field lacks a standardized and systematic benchmarking framework for evaluating generative models across diverse conditions. To address this gap, we introduce the Conditional Time Series Generation
Benchmark (ConTSG-Bench). ConTSG-Bench comprises a large-scale, well-aligned
dataset spanning diverse conditioning modalities and levels of semantic abstraction, first enabling systematic evaluation of representative generation methods across these dimensions with a comprehensive suite of metrics for generation fidelity and condition adherence. Both the quantitative benchmarking and in-depth analyses of conditional generation behaviors have revealed the traits and limitations of the current approaches, highlighting critical challenges and promising research directions, particularly with respect to precise structural controllability and downstream task utility under complex conditions.
Read the full abstract ▾
All authors Shaocheng Lan, Shuqi Gu, Zhangzhi Xiong, Kan Ren
Machine Learning · Cross-listed from cs.CV
Evaluating GPT-5 as a Multimodal Clinical Reasoner: A Landscape Commentary
Alexandru Florea, Shansong Wang, Mingzhe Hu et al. (+5 more)
The transition from task-specific artificial intelligence toward general-purpose foundation models raises fundamental questions about their capacity to support the integrated
reasoning required in clinical medicine, where diagnosis demands synthesis of ambiguous patient narratives, laboratory data, and
multimodal imaging. This landscape commentary provides the first controlled, cross-sectional evaluation of the GPT-5 family (GPT-5, GPT-5 Mini, GPT-5 Nano) against its predecessor GPT-4o across a diverse spectrum of clinically grounded tasks, including medical education examinations, text-based
reasoning benchmarks, and visual question-answering in neuroradiology, digital pathology, and mammography using a standardized zero-shot chain-of-thought protocol. GPT-5 demonstrated substantial gains in expert-level textual
reasoning, with absolute improvements exceeding 25 percentage-points on MedXpertQA. When tasked with
multimodal synthesis, GPT-5 effectively leveraged this enhanced
reasoning capacity to ground uncertain clinical narratives in concrete imaging evidence, achieving state-of-the-art or competitive performance across most VQA
benchmarks and outperforming GPT-4o by margins of 10-40% in mammography tasks requiring fine-grained lesion characterization. However, performance remained moderate in neuroradiology (44% macro-average accuracy) and lagged behind domain-specific models in mammography, where specialized systems exceed 80% accuracy compared to GPT-5's 52-64%. These findings indicate that while GPT-5 represents a meaningful advance toward integrated
multimodal clinical
reasoning, mirroring the clinician's cognitive process of biasing uncertain information with objective findings, generalist models are not yet substitutes for purpose-built systems in highly specialized, perception-critical tasks.
Read the full abstract ▾
All authors Alexandru Florea, Shansong Wang, Mingzhe Hu, Qiang Li, Zach Eidex, Luke del Balzo, Mojtaba Safari, Xiaofeng Yang
Machine Learning
KindSleep: Knowledge-Informed Diagnosis of Obstructive Sleep Apnea from Oximetry
Micky C Nnamdi, Wenqi Shi, Cheng Wan et al. (+4 more)
Obstructive sleep apnea (OSA) is a sleep disorder that affects nearly one billion people globally and significantly elevates cardiovascular risk. Traditional diagnosis through polysomnography is resource-intensive and limits widespread access, creating a critical need for accurate and efficient alternatives. In this paper, we introduce KindSleep, a deep learning framework that integrates clinical knowledge with single-channel patient-specific oximetry signals and clinical data for precise OSA diagnosis. KindSleep first learns to identify clinically interpretable concepts, such as desaturation indices and respiratory disturbance events, directly from raw oximetry signals. It then fuses these AI-derived concepts with
multimodal clinical data to estimate the Apnea-Hypopnea Index (AHI). We evaluate KindSleep on three large, independent
datasets from the National Sleep Research Resource (SHHS, CFS, MrOS; total n = 9,815). KindSleep demonstrates excellent performance in estimating AHI scores (R2 = 0.917, ICC = 0.957) and consistently outperforms existing approaches in classifying OSA severity, achieving weighted F1-scores from 0.827 to 0.941 across diverse populations. By grounding its predictions in a layer of clinically meaningful concepts, KindSleep provides a more transparent and trustworthy diagnostic tool for sleep medicine practices.
Read the full abstract ▾
All authors Micky C Nnamdi, Wenqi Shi, Cheng Wan, J. Ben Tamo, Benjamin M Smith, Chad A Purnell, May D Wang
Machine Learning · Cross-listed from cs.AI
CONE: Embeddings for Complex Numerical Data Preserving Unit and Variable Semantics
Gyanendra Shrestha, Anna Pyayt and Michael Gubanov
Large pre-trained models (LMs) and Large
Language Models (LLMs) are typically effective at capturing
language semantics and contextual relationships. However, these models encounter challenges in maintaining optimal performance on tasks involving numbers. Blindly treating numerical or structured data as terms is inadequate – their semantics must be well understood and encoded by the models. In this paper, we propose CONE, a hybrid
transformer encoder pre-trained model that encodes numbers, ranges, and gaussians into an
embedding vector space preserving distance. We introduce a novel composite
embedding construction
algorithm that integrates numerical values, ranges or gaussians together with their associated units and attribute names to precisely capture their intricate semantics. We conduct extensive experimental evaluation on large-scale
datasets across diverse domains (web, medical, finance, and government) that justifies CONE's strong numerical
reasoning capabilities, achieving an F1 score of 87.28% on DROP, a remarkable improvement of up to 9.37% in F1 over state-of-the-art (SOTA) baselines, and outperforming major SOTA models with a significant Recall@10 gain of up to 25%.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Baoqing Yue, Zihan Zhu, Yutong Han et al. (+6 more)
Existing
reasoning evaluation paradigms suffer from different limitations: fixed
benchmarks are increasingly saturated and vulnerable to contamination, while preference-based evaluations rely on subjective judgments. We argue that a core aspect of intelligence is the ability to decide what information to acquire and how to use it effectively. We propose Interactive
Benchmarks, a unified evaluation paradigm that assesses a model's
reasoning ability through budgeted multi-turn interaction. We evaluate models under this framework in two settings: Interactive Proofs, where models interact with a judge to solve Logic, UI2Html, and Mathematics tasks under objective feedback; and Interactive Games, where models reason strategically to maximize long-horizon utilities. Our results show that interactive
benchmarks provide a more robust assessment of this dimension of model intelligence, revealing substantial room for improvement in interactive scenarios.
Read the full abstract ▾
All authors Baoqing Yue, Zihan Zhu, Yutong Han, Brian Fan, Qian Sun, Jichen Feng, Hufei Yang, Yifan Zhang, Mengdi Wang