Ax Ivan Sedykh, Nikita Sorokin, Valentin Malykh 17h ago

Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models

Model scheduling for masked diffusion language models uses smaller models at early denoising steps for faster generation.

Ax Mohammad Rezaei, Jens Lehmann, Sahar Vahdati 17h ago

LLM Reasoning with Process Rewards for Outcome-Guided Steps

Process reward models improve LLM mathematical reasoning by providing step-level feedback on intermediate errors, not just final outcomes.

Ax Mahdi Tavassoli Kejani, Fadi Dornaika, Charlotte Laclau, Jean-Michel Loubes 17h ago

Homophily-aware Supervised Contrastive Counterfactual Augmented Fair Graph Neural Network

Fairness-aware GNN training using contrastive learning and counterfactual augmentation to mitigate biases from graph structure.

Ax Roy Rinberg, Annabelle Michael Carrell, Simon Henniger, Nicholas Carlini, Keri Warr 17h ago

Haiku to Opus in Just 10 bits: LLMs Unlock Massive Compression Gains

LLM-based compression using domain-adapted LoRA for lossless and lossy text compression achieving 2x improvements.

Ax J\k{e}drzej Maczan 17h ago

Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers

Systematic characterization of WebGPU dispatch overhead for LLM inference across GPU vendors, backends, and browsers at batch size 1.

Ax Mengzhou Wu, Yuzhe Guo, Yuan Cao, Haochuan Lu, Songhe Zhu, Pingzhe Qu, Xin Chen, Kang Qin, Zhongpu Wang, Xiaode Zhang, Xinyi Wang, Wei Dai, Gang Cao, Yuetang Deng, Zhi Gong, Dezhi Ran, Linyi Li, Wei Yang, Tao Xie 17h ago

UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics

UI-Oceanus framework scales GUI agents via synthetic environmental dynamics and self-supervised learning instead of costly human demonstrations.

Ax Tianyu Liu, Sihan Jiang, Fan Zhang, Kunyang Sun, Teresa Head-Gordon, Hongyu Zhao 17h ago

DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery

Benchmark evaluating LLM and embedding performance for drug discovery tasks, assessing advantages over traditional methods.

Ax Qingzhong Li, Yue Hu, Zhou Long, Qingchang Ma, Hui Ma, Jinhai Sa 17h ago

FTimeXer: Frequency-aware Time-series Transformer with Exogenous variables for Robust Carbon Footprint Forecasting

Frequency-aware Transformer for carbon footprint forecasting in power grids using periodic patterns and exogenous variables.

Ax Andr\'e Biedenkapp 17h ago

Contextual Intelligence The Next Leap for Reinforcement Learning

Contextual RL improves agent generalization by exposing agents to environment characteristics for better zero-shot transfer beyond training distribution.

Ax Yiqin Yang, Hao Hu, Yihuan Mao, Jin Zhang, Chengjie Wu, Yuhua Jiang, Xu Yang, Runpeng Xie, Yi Fan, Bo Liu, Yang Gao, Bo Xu, Chongjie Zhang 17h ago

OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration

OPRIDE method for offline preference-based RL reducing human feedback queries through efficient in-dataset exploration strategies.

Ax Venkatakrishna Reddy Oruganti 17h ago

Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility

Differentiable Symbolic Planning architecture combining neural networks with discrete symbolic reasoning for constraint satisfaction problems.

Ax Naimur Rahman, Naazreen Tabassum 17h ago

Modeling and Controlling Deployment Reliability under Temporal Distribution Shift

Framework for modeling and controlling ML model reliability under temporal distribution shift during deployment with continuous monitoring.

Ax Sophie Weidmann, Fernando Castor 17h ago

An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code

Contrastive prompt tuning method to optimize LLMs for generating energy-efficient code aligned with Green Software Development goals.

Ax Thomas Pravetz 17h ago

Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning

PRISM framework for zero-shot policy transfer in RL using interpretable concept clustering with causal validation across different algorithms.

Ax Han Song, Yucheng Zhou, Jianbing Shen, Yu Cheng 17h ago

From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation

Entropy-based analysis of combining Chain-of-Thought with RL for text-to-image generation, showing exploration-optimization tradeoffs.

Ax Mostapha Benhenda 17h ago

YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches

Live benchmark dataset for forecasting startup success using Y Combinator batches with three-month evaluation cycles.

Ax Alex Al\`i Maleknia, Yuzuru Sato 17h ago

Dynamical structure of vanishing gradient and overfitting in multi-layer perceptrons

Dynamical systems analysis of vanishing gradient and overfitting in multi-layer perceptrons using minimal models.

Ax Timothy Gould, Sidike Paheding 17h ago

Self-Directed Task Identification

Self-Directed Task Identification framework enabling models to autonomously identify target variables in zero-shot settings without pretraining.

Ax Alex E. Ballentine, Nachiket U. Bapat, Raghvendra V. Cowlagi 17h ago

Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models

Physics-informed deep generative models for offline RL in spaceflight to mitigate sim-to-real gap with limited real-world training data.

Ax Chin-Chia Michael Yeh 17h ago

Matrix Profile for Time-Series Anomaly Detection: A Reproducible Open-Source Benchmark on TSB-AD

Open-source benchmarking of Matrix Profile methods for time-series anomaly detection on univariate and multivariate datasets.

Ax Aaditya Naik, Guruprerana Shabadi, Rajeev Alur, Mayur Naik 17h ago

Do We Need Frontier Models to Verify Mathematical Proofs?

Study comparing frontier vs smaller LLMs for mathematical proof verification, evaluating whether expensive models are necessary for proof checking.

Ax Jun-Sik Yoo 17h ago

On the Geometric Structure of Layer Updates in Deep Language Models

Analysis of layer-to-layer representation changes in language models, decomposing updates into tokenwise and residual components.

Ax Vamshi Guduguntla, Kavin Soni, Debanshu Das 17h ago

VALOR: Value-Aware Revenue Uplift Modeling with Treatment-Gated Representation for B2B Sales

VALOR framework for B2B sales revenue uplift modeling handling zero-inflated distributions with treatment-gated representation learning.

Ax Jonathon Hirschi 17h ago

Time-Warping Recurrent Neural Networks for Transfer Learning

Transfer learning method for RNNs using time-warping rescaling, with theoretical analysis for linear differential equation models.

Ax Kun Zhang, Jiaqi Sun, Yiqing Li, Ignavier Ng, Namrata Deka, Shaoan Xie 17h ago

SEDGE: Structural Extrapolated Data Generation

Framework for generating synthetic data under specified conditions with approximate identifiability guarantees for data distribution extrapolation.

Ax Marco Ruiz, Miguel Arana-Catania, David R. Ardila, Rodrigo Ventura 17h ago

Causal-Audit: A Framework for Risk Assessment of Assumption Violations in Time-Series Causal Discovery

Framework for validating assumptions in time-series causal discovery through calibrated risk assessment and effect-size diagnostics.

Ax Arka Jain, Umesh Sharma 17h ago

Re-analysis of the Human Transcription Factor Atlas Recovers TF-Specific Signatures from Pooled Single-Cell Screens with Missing Controls

Re-analysis of transcription factor atlas single-cell perturbation screen with improved quality control pipeline and MORF barcode demultiplexing.

Ax Seonggon Kim, Alireza Khodamoradi, Kristof Denolf, Eunhyeok Park 17h ago

AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation

Low-precision training method for LLMs using adaptive Hadamard transforms based on outlier patterns in weights, activations, and gradients.

Ax Adam Bayley, Xiaodan Zhu, Raquel Aoki, Yanshuai Cao, Kevin H. Wilson 17h ago

Jump Start or False Start? A Theoretical and Empirical Evaluation of LLM-initialized Bandits

Research on using LLM-generated synthetic data to warm-start contextual bandits, examining alignment between LLM choices and actual user preferences.

Ax Zeyang Huang, Angelos Chatzimparmpas, Thomas H\"ollt, Takanori Fujiwara 17h ago

A Spectral Framework for Multi-Scale Nonlinear Dimensionality Reduction

Spectral framework for multi-scale nonlinear dimensionality reduction balancing global-local structure preservation and expressiveness-transparency.

Ax Xiangbo Qi, Chaoyi Jiang, Murali Annavaram 17h ago

Fast NF4 Dequantization Kernels for Large Language Model Inference

Optimized NF4 dequantization kernels for fast LLM inference on NVIDIA GPUs, addressing FP16 conversion bottleneck.

Ax Xiaoxing Ren, Yuwen Ma, Nicola Bastianello, Karl H. Johansson, Thomas Parisini, Andreas A. Malikopoulos 17h ago

Communication-Efficient Distributed Learning with Differential Privacy

Communication-efficient distributed learning algorithm with differential privacy using local training and gradient clipping.

Ax Gonzalo Uribarri 17h ago

ROMAN: A Multiscale Routing Operator for Convolutional Time Series Models

ROMAN operator for time series that creates multiscale representations by building antialiased pyramids for convolutional classifiers.

Ax Yan Zheng, Florian Bordes 17h ago

VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation

VoxelCodeBench platform benchmarking code generation models for 3D spatial reasoning with execution in Unreal Engine.

Ax Mohammed Suhail B Nadaf 17h ago

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens

Analysis of function vectors in LLMs showing they steer behavior beyond logit lens interpretability across 4,032 cross-template transfer pairs.

Ax Samuel Honor, Mohamed Abdelnaby, Kevin Leahy 17h ago

Complex-Valued GNNs for Distributed Basis-Invariant Control of Planar Systems

Complex-valued GNNs for distributed control of networked systems with basis-invariance for GPS and compass-denied environments.

Ax Lei Song, Shihan Guan, Youyong Kong 17h ago

Analytic Drift Resister for Non-Exemplar Continual Graph Learning

Continual graph learning without storing exemplars, using class-level prototypes and analytic continual learning to address catastrophic forgetting.

Ax Yasushi Nishida 17h ago

AXELRAM: Quantize Once, Never Dequantize

AXELRAM smart SRAM architecture computing attention scores from quantized KV cache without dequantization using orthogonal-transform quantization.

Ax Cunyang Wei, Siddharth Singh, Aishwarya Sarkar, Daniel Nichols, Tisha Patel, Aditya K. Ranjan, Sayan Ghosh, Ali Jannesari, Nathan R. Tallent, Abhinav Bhatele 17h ago

Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training

Distributed GNN training with communication-free sampling and 4D hybrid parallelism for scaling mini-batch learning on large graphs.

Ax Haruhi Shida, Koo Imai, Keigo Kansa 17h ago

Generalization Limits of Reinforcement Learning Alignment

Study of generalization limits in RLHF alignment, proposing compound jailbreaks targeting LLM safety through redistribution of existing capabilities.

Ax Eric Gan 17h ago

Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability

Theoretical analysis of gradient descent training at edge of stability with product-stability property for convergence guarantees.

Ax Farhad Pourkamali-Anaraki 17h ago

Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration

Low-rank compression of pretrained models using randomized subspace iteration for efficient SVD-based model reduction.

Ax Jeesuk Shin, Donggyun Seo, Sihyeong Yu, Joongoo Jeon 17h ago

A Numerical Method for Coupling Parameterized Physics-Informed Neural Networks and FDM for Advanced Thermal-Hydraulic System Simulation

Physics-informed neural networks coupled with finite difference methods for thermal-hydraulic system simulation.

Ax Zitao Lin, Chang Zhu, Wei Meng 17h ago

Cross-subject Muscle Fatigue Detection via Adversarial and Supervised Contrastive Learning with Inception-Attention Network

Muscle fatigue detection from sEMG signals using adversarial and contrastive learning with neural networks.

Ax Matthew Levinson 17h ago

Finding Belief Geometries with Sparse Autoencoders

Mechanistic interpretability research on whether LLMs encode belief geometries like transformers trained on hidden Markov models.

Ax Yuheng Zhang, Mingyue Huo, Minghao Zhu, Mengxue Zhang, Nan Jiang 17h ago

Beyond Semantic Manipulation: Token-Space Attacks on Reward Models

Token-space attacks on reward models used in RLHF, introducing TOMPA framework for adversarial optimization beyond semantic manipulation.

Ax Haowen Wan, Qianqian Yang 17h ago

Adaptive Semantic Communication for Wireless Image Transmission Leveraging Mixture-of-Experts Mechanism

Semantic communication for wireless image transmission using mixture-of-experts to adapt to diverse image contents and channel conditions.

Ax Haijian Shao, Dalong Zhao, Xing Deng, Wenzheng Zhu, Yingtao Jiang 17h ago

LieTrunc-QNN: Lie Algebra Truncation and Quantum Expressivity Phase Transition from LiePrune to Provably Stable Quantum Neural Networks

Algebraic-geometric framework for quantum neural networks addressing barren plateaus and noise robustness.

Ax Qingxiu Liu, Cyril Y. He, Hanser Jiang, Zion Wang, Alan Zhao, Patrick P. C. Lee 17h ago

FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving

FluxMoE system decouples expert residency to improve inference serving throughput in Mixture-of-Experts LLMs.

Ax Patrick Pynadath, Jiaxin Shi, Ruqi Zhang 17h ago

Generative Frontiers: Why Evaluation Matters for Diffusion Language Models

Technical analysis of evaluation methodology challenges for diffusion language models at scale.