MIRAGE uses targeted adversarial perturbations in representation space to cause content moderation classifiers to flag images as policy-violating, achieving over 88% success rate.

Anshul Nasery, Ramnath Kumar, Cho-Jui Hsieh et al.

This study introduces a low-resource end-to-end Algerian dialect speech-to-speech system using Whisper, achieving 13.74% WER, integrating ASR, NLU, RAG, and TTS.

Dihia Lanasri, Fairouz Taki, Asma Kemmoum

Autodata uses meta-optimized agentic data scientists to generate high-quality synthetic data, significantly improving model performance.

Ilia Kulikov, Chenxi Whitehouse, Tianhao Wu et al.

Proposes KCas, a reverse knowledge distillation framework transferring statistical parameters from small to large models, reducing computational cost in nonparametric multivariate estimation.

Luyang Fang, Haoran Lu, Yongkai Chen et al.

Benchmarking 17 deep models for large-scale code retrieval; introducing LLM-based normalization and rewriting improves recall by up to 29%.

Leonardo Venuta, Francesco Tosoni, Paolo Ferragina

UniTeD introduces a joint temporal diffusion model for perception and planning, achieving state-of-the-art results with 90.24 PDMS on NAVSIM v1.

Bo Zhao, Xinting Zhao, Naifan Li et al.

Proposed SSMNBench, a diagnostic benchmark with 3300 QA pairs, distinguishes single-view sufficiency and multi-view necessity to evaluate cross-view understanding of 17 models.

Tianchen Guo, Chen Liu, Ling Chen et al.

LCG uses Sparse Relational Attention for consistent long-context image generation, improving consistency and scalability.

Zihao Wang, Yijia Xu, Haoze Zheng et al.

ScaleHP optimizes coupled errors in camera-space hand pose estimation, achieving 35.8mm CS-MPJPE on FreiHand.

Ruitao Jing, Xingyu Chen, Hongyang Li et al.

VPA-Guard combines retrieval-augmented reasoning and self-evolution to reduce visual prompt attack success rates by 44.2%, enhancing video generation safety.

Yining Sun, Haoyu Kang, Jiajun Wu et al.

BLOCK replaces model bottleneck layers with trained transcoders for persistent concept removal in SD3.5, Flux, Infinity, outperforming state-of-the-art methods.

Aditya Kumar, Pierre Joly, Adam Dziedzic et al.

ASSCG uses RWKV for adaptive gating in fast-slow systems, achieving +2.28 score and 60% latency reduction on nuPlan Hard20.

Sining Ang, Yuan Chen, Liu Haiyan et al.

C3-Bench creates a multi-domain change captioning benchmark with 51 real-world scenarios, integrating LLM-based fine-grained evaluation for robustness.

Jae-Woo Kim, Hyeongbeom Kim, Ue-Hwan Kim

Proposes Teach-to-Reason (T2R), a framework using self-improving teachers and contrastive supervision to enhance reasoning in CXR VQA, outperforming baselines.

Xiao Han, Hao Liu, Zhimin Bao et al.

Hybrid-IR combines graph-based and dense retrieval with iterative reasoning, achieving 10% accuracy improvement on medical QA benchmarks.

Sheng Wan, Jiahui Zhang, Zicheng Zhao et al.

MM-R2 framework improves accuracy in multimodal RAG by reasoning before retrieval.

Tianyu Yang, Shir Simon, Zhenzhen Li et al.

EvoFlock employs multi-objective genetic algorithms to automatically optimize 15 parameters of multi-agent flocking models, achieving behaviors aligned with user-defined metrics.

Craig Reynolds

ASAP integrates diverse optimizers with agent-system co-design, optimizing wall-clock time for ML hyperparameter tuning.

Taicheng Guo, Haomin Zhuang, Kehan Guo et al.

RAVEN uses visual embeddings as long-term memory for scalable robot reasoning and navigation.

Yixun Hu, Zhicheng Zheng, Lihan Zha et al.

Proposes a training-free method using intermediate-layer entropy trajectories to detect jailbreak prompts, achieving AUROC up to 0.94 across Llama, Qwen, and Gemma.

Sofiia Nikolenko, Michele Papucci, Mina Rezaei et al.