Tracked topic
…Specifically, RACES improves DeepSeek-R1-Distill-Qwen-14B by an average of 3.1 points (from 48.2 to 51.3) and boosts Qwen3-14B performance from 58.8 to 61.1…
…Across AFTraj-2K and an external Who\&When benchmark, AgentForesight-7B outperforms leading proprietary models, including GPT-4.1 and DeepSeek-V4-Pro , achieving up to +19.9% performance gain and 3times…
…Our results show that posts proposing new languages for avoiding oversight are judged by DeepSeek-3.2 as being less aligned than the other categories and that all languages can be learned…
…blog post, check it out! This podcast is generated via ngxson/kokoro-podcast-generator , using DeepSeek-R1 and Kokoro-TTS Really enjoyed reading The AI Tools for Art Newsletter—such a well…
…the median reference solution grows from 67 to 374 lines, the median number of executed commands grows from 40 to 244, and DeepSeek-V4-Pro pass@4 drops from 90% at R1…
…Thank you. 📻 🎙️ Hey, I generated an AI podcast about this blog post, check it out! This podcast is generated via ngxson/kokoro-podcast-generator , using DeepSeek-R1 and Kokoro-TTS . · No…
…Otherwise use reasoning-format flag and pass DeepSeek value to get pure tokens Now I can use llama.cpp all the time. A big thank you to the devs. Is there currently…
…It reduces the token usage of DeepSeek-R1-Distill-Qwen-7B by approximately 56% while maintaining state-of-the-art accuracy. View arXiv page View PDF GitHub 12 Add to collection Community…
…Empirically, Pythagoras-Prover-4B surpasses DeepSeek-Prover-V2-671B at pass@32 on MiniF2F-Test (86.1% vs 82.4%) with ~167x fewer parameters, while Pythagoras-Prover-32B sets the open-source…
…On DeepSeek-R1-Distill-Qwen-7B trained for mathematical reasoning , ESPO surpasses PPO on AIME~2024 (46.28% vs. 45.25%), AMC~2023 (85.83% vs. 82.94%), and MATH-500 (87…