Argues that real attackers rely on simple tactics rather than gradient-based methods, highlighting gaps between adversarial ML research and practice.

Giovanni Apruzzese, Hyrum S. Anderson, Savino Dambra et al.

AER model combines auto-encoder and regression, achieving a 23.5% F1 score improvement for time series anomaly detection.

Lawrence Wong, Dongyu Liu, Laure Berti-Equille et al.

Integrates IAIMM-KF and MPC for multi-modal obstacle uncertainty prediction, enhancing autonomous vehicle safety in complex traffic.

Jian Zhou, Björn Olofsson, Erik Frisk

Proposes Tune-A-Video, a one-shot tuning method for text-to-video generation using pretrained diffusion models, achieving high content consistency with minimal fine-tuning.

Jay Zhangjie Wu, Yixiao Ge, Xintao Wang et al.

Self-Instruct uses model self-generated instructions to improve instruction tuning, boosting GPT-3 performance by 33%.

Yizhong Wang, Yeganeh Kordi, Swaroop Mishra et al.

This paper reveals that Transformer attention embodies a dual form of gradient descent, interpreting in-context learning (ICL) as implicit fine-tuning, validated through empirical analysis and a momentum attention mechanism.

Damai Dai, Yutao Sun, Li Dong et al.

HyDE combines instruction-guided generation and contrastive encoding for zero-shot dense retrieval without relevance labels.

Luyu Gao, Xueguang Ma, Jimmy Lin et al.

Survey on reasoning in LLMs, highlighting Chain-of-Thought prompting, achieving 74.4% on GSM8K.

Jie Huang, Kevin Chen-Chuan Chang

Proposes Fine-tune-CoT, using large models to generate reasoning samples, greatly enhancing small model reasoning performance.

Namgyu Ho, Laura Schmid, Se-Young Yun

HALIE framework evaluates human-AI interaction, revealing that superior non-interactive metrics do not guarantee better user experience.

Mina Lee, Megha Srivastava, Amelia Hardy et al.

INSTRUCTOR is a single text embedding model using instruction finetuning, achieving 3.4% improvement across 70 tasks without further training.

Hongjin Su, Weijia Shi, Jungo Kasai et al.

This study establishes that 4-bit quantization offers near-universal optimality for zero-shot performance and model size trade-offs in large language models, validated by 35,000 experiments.

Tim Dettmers, Luke Zettlemoyer

Proposes an unsupervised optimal transport-based hallucination detector for NMT, outperforming previous model-based and external methods.

Nuno M. Guerreiro, Pierre Colombo, Pablo Piantanida et al.

Proposed PROMPTIST, a reinforcement learning framework, improves text-to-image prompts, boosting reward by over 30% on Stable Diffusion.

Yaru Hao, Zewen Chi, Li Dong et al.

Pre-trained BERT-based neural rankers outperform traditional methods in medical systematic review screening prioritization, with significant improvements in key metrics.

Shuai Wang, Harrisen Scells, Bevan Koopman et al.

Using internal source contribution (ALTI+) and cross-lingual embeddings (LaBSE) improves hallucination detection accuracy by 2x, with enhanced reranking strategies.

David Dale, Elena Voita, Loïc Barrault et al.

Proposes transformed Gaussian process-driven Cox models on linear networks, introducing three classes (log Gaussian, interrupted, permanental), with novel simulation and inference algorithms.

Jesper Møller, Jakob G. Rasmussen

Deep RL with motion primitives enables efficient, robust UAV path planning for active target sensing, outperforming heuristics.

Harsh Goel, Laura Jarin Lipschitz, Saurav Agarwal et al.

Waymo's Collision Avoidance Testing (CAT) framework evaluates SAE Level 4 ADS safety in urgent scenarios via virtual simulation and behavior models, showing a 15% collision reduction.

Kristofer D. Kusano, Kurt Beatty, Scott Schnelle et al.

This study evaluates zero-shot Chain-of-Thought prompting's bias and toxicity, revealing larger models exhibit increased social biases.

Omar Shaikh, Hongxin Zhang, William Held et al.