A cost-aware evasion framework reveals robustness gaps in phishing detection; median evasion cost is 2, with over 80% attacks on three low-cost features.

Julian Allagan, Mohamed Elbakary, Zohreh Safari et al.

The paper introduces a maximum-entropy exploration method using future state-action visitation measures, improving feature visitation and convergence speed.

Adrien Bolland, Gaspard Lambrechts, Damien Ernst

ALIGN uses adversarial learning to enhance cross-session generalization in speech neuroprostheses, significantly reducing phoneme and word error rates.

Zhanqi Zhang, Shun Li, Bernardo L. Sabatini et al.

RAMP uses reinforcement learning for adaptive mixed-precision quantization, achieving 6% size and 1-3% quality improvements for on-device LLM inference.

Arpit Singh Gautam, Saurabh Jha

Efficient reasoning in small LLMs using LoRA adapters and RL, significantly reducing response length.

Yelysei Bondarenko, Thomas Hehn, Rob Hesselink et al.

HorizonMath evaluates AI progress in mathematical discovery using an automated verification framework, with GPT 5.4 Pro achieving breakthroughs on two problems.

Erik Y. Wang, Sumeet Motwani, James V. Roggeveen et al.

Effective distillation of xLSTM architectures recovers and exceeds teacher model performance.

Lukas Hauzenberger, Niklas Schmidinger, Thomas Schmied et al.

PokeAgent Challenge tests AI decision-making via Pokemon battles and RPG, offering a 20M+ dataset and standardized evaluation framework.

Seth Karten, Jake Grigsby, Tersoo Upaa et al.

PhysMoDPO optimizes humanoid motion for physical realism and task performance through preference optimization.

Yangsong Zhang, Anujith Muraleedharan, Rikhat Akizhanov et al.

Using Joint Embedding Predictive Architectures (JEPA) for learning representations in latent space significantly enhances parameter estimation accuracy.

Helen Qu, Rudy Morel, Michael McCabe et al.

Using CWRF, only critical weights are adjusted to enhance privacy while maintaining utility.

Xingli Fang, Jung-Eun Kim

MXNorm reuses MXFP8 block scales for efficient tensor normalization, reducing reduction size by 32x.

Callum McLean, Luke Y. Prince, Alexandre Payot et al.

ZO-SAM integrates zero-order optimization to reduce computational costs, enhancing efficiency and robustness in sparse training.

Jie Ji, Gen Li, Kaiyuan Deng et al.

BoSS enhances deep active learning performance by integrating multiple selection strategies, excelling on large-scale datasets.

Denis Huseljic, Paul Hahn, Marek Herde et al.

Zero-hyperparameter multi-corner analysis using learned priors reduces validation cost by over 10 times.

Wei W. Xing, Kaiqi Huang, Jiazhan Liu et al.

Influence Malleability in Linearized Attention: Dual Implications of Non-Convergent NTK Dynamics.

Jose Marie Antonio Miñoza, Paulo Mario P. Medina, Sebastian C. Ibañez

DDIM reverse chain as Partitioned Iterated Function Systems provides a unified design language for denoising diffusion models.

Ann Dooms

Achieve color control in FLUX's VAE latent space, revealing a structure reflecting Hue, Saturation, and Lightness.

Mateusz Pach, Jessica Bader, Quentin Bouniot et al.

Separable Neural Architectures (SNA) unify predictive and generative intelligence by constraining interaction order and tensor rank.

Reza T. Batley, Apurba Sarker, Rajib Mostakim et al.

STAMP framework uses the Polar mechanism to achieve superior privacy-utility trade-offs in text privacy.

Fengwei Tian, Payel Bhattacharjee, Heidi Hanson et al.