ESPnet-SpeechLM: An Open Speech Language Model Toolkit ESPnet-SpeechLM is an open-source toolkit for developing Speech Language Models (SpeechLMs) and voice-driven applications. It simplifies speech processing by framing tasks as sequential modeling problems, automating data
LLMS
-
Cost-Efficient Collaboration Between On-Device and Cloud Language Models
By
–
Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models This paper explores a cost-efficient collaboration between small, on-device language models (LMs) and large, cloud-hosted LMs for data-intensive tasks. The MinionS protocol improves task
-
Bi’an: Bilingual Benchmark for RAG Hallucination Detection
By
–
Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generation Bi’an introduces a bilingual benchmark dataset (Bi’anBench) and lightweight judge models for hallucination detection in Retrieval-Augmented Generation (RAG). The dataset spans
-
SWE-RL: Enhancing LLM Reasoning Through Software Evolution
By
–
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution SWE-RL is a reinforcement learning (RL) approach that enhances LLM reasoning for software engineering by learning from open-source software evolution data. It trains Llama3-SWE-RL-70B on GitHub
-
FFTNet: Efficient FFT-Based Alternative to Self-Attention
By
–
The FFT Strikes Back: An Efficient Alternative to Self-Attention FFTNet replaces self-attention with an efficient O(n log n) spectral filtering approach using the Fast Fourier Transform (FFT). By operating in the frequency domain, it captures long-range dependencies while a
-
AI Co-Scientists and LLM Reasoning Advances This Week
By
–
This week, AI is stepping into new dimensions—becoming co-scientists, sculpting 3D avatars, and blending cloud and on-device models into a seamless dance of creativity and efficiency. – Towards an AI co-scientist
– SWE-RL: Advancing LLM Reasoning via Reinforcement Learning -
Building Production-Ready RAG Systems with Qdrant FastAPI
By
–
RAG Pipeline Guide Learn to build production-ready RAG systems using Qdrant vector DB, FastAPI, and LangChain's LCEL for sophisticated retrieval chains. Key features:
– Async vector search
– Type-safe FastAPI endpoints
– LCEL RAG pipelines Start building better RAG systems! -
Claude 4.5 handles topic changes naturally
By
–
You can feel when a topic change breaks a model. 4.5 handles it very naturally.
-
Extended AI Conversations Demonstrate Coherence and Topic Versatility
By
–
I have a two-day long chat spanning so many topics. It's so good (and still completely coherent).
-
o3-mini-high excels in its specialized niche
By
–
Yes, o3-mini-high is definitely good at its own niche.