Search: Community trading

Paper page - What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion

…View arXiv page View PDF Project page GitHub 127 Add to collection Community 🚀 PAE: State-of-the-Art Latent Diffusion with 13x Faster Training! We are excited to present Prior-Aligned AutoEncoder…

May 11, 2026

Paper page - Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replay

…View arXiv page View PDF Project page GitHub 549 Add to collection Community code: https://github.com/nossa-y/activity-frames project: https://usenocta.app paper: https://arxiv.org/abs/2608.05784…

Aug 7, 2026

Paper page - Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

…View arXiv page View PDF GitHub 6 Add to collection Community Grammar-constrained decoding techniques used to ensure syntactic validity in code generation can be exploited as an attack surface, leading to…

Jun 11, 2026

Paper page - SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue

…View arXiv page View PDF Project page Add to collection Community Zero-shot text-to-speech (TTS) has improved substantially for single-speaker synthesis, yet expressive long-form multi-speaker dialogue remains…

Jun 1, 2026

Paper page - RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation

…We also introduce Meno-Lite-0.1, a 7B domain-adapted model with a strong cost--performance trade-off , and analyse MTRAGEval, highlighting annotation limitations and directions for improvement. Our code is…

May 8, 2026

Paper page - To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing

…View arXiv page View PDF Add to collection Community A lot of AI-generated patches feel like slop because frontier models still struggle with something we barely consider a task at all…

Aug 4, 2026

Paper page - ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving

…View arXiv page View PDF Add to collection Community We started ReflectDrive-2 from a concrete observation: when imitation-learned driving policies fail, they fail along two predictable axes — longitudinal (overshoot, late…

May 8, 2026

Paper page - Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models

…View arXiv page View PDF Project page GitHub 68 Add to collection Community 🌊 Excited to share TIDE — to our knowledge, the first framework for cross-architecture distillation of diffusion LLMs, where teacher…

Apr 30, 2026

Paper page - Large Language Models Explore by Latent Distilling

…the trade-off between diversity and coherence in creative writing. Our code has released at: https://github.com/LinesHogan/tLLM. View arXiv page View PDF GitHub 39 Add to collection Community We…

Apr 29, 2026

Paper page - VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon

…In doing so, VLA-Corrector mitigates the trade-off imposed by static horizons between execution robustness and policy-call frequency. It can be integrated into different VLA models without further retraining the…

Jul 6, 2026

Followed topics