| BitNet b1.58 2B4T Technical Report | Apr 16, 2025 | Computational EfficiencyCPU | —Unverified | 0 |
| Generative Recommendation with Continuous-Token Diffusion | Apr 16, 2025 | DenoisingLanguage Modeling | —Unverified | 0 |
| Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification | Apr 16, 2025 | Large Language ModelSentiment Analysis | —Unverified | 0 |
| Rethinking LLM-Based Recommendations: A Query Generation-Based, Training-Free Approach | Apr 16, 2025 | DiversityLanguage Modeling | —Unverified | 0 |
| AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection | Apr 16, 2025 | Anomaly DetectionLarge Language Model | CodeCode Available | 1 |
| Modular-Cam: Modular Dynamic Camera-view Video Generation with LLM | Apr 16, 2025 | Large Language ModelText-to-Video Generation | —Unverified | 0 |
| Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures | Apr 16, 2025 | CPUGPU | —Unverified | 0 |
| Towards Conversational AI for Human-Machine Collaborative MLOps | Apr 16, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| HLS-Eval: A Benchmark and Framework for Evaluating LLMs on High-Level Synthesis Design Tasks | Apr 16, 2025 | High-Level SynthesisLarge Language Model | CodeCode Available | 1 |
| Position: The Most Expensive Part of an LLM should be its Training Data | Apr 16, 2025 | Large Language ModelPosition | —Unverified | 0 |
