💬 LLMs

GPT, Prompt Engineering, Fine-tuning, Embeddings

DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token viaReinforcement Learning
paperium.net·2d·
Discuss: DEV
🤖AI
Flag this post
Imagine changing your app's behaviour... without changing the code. (Part 2)
lnkd.in·1h·
Discuss: DEV
🤖AI
Flag this post
Building AI Agents in Kotlin – Part 1: A Minimal Coding Agent
blog.jetbrains.com·15h
🤖AI
Flag this post
TimeSense:Making Large Language Models Proficient in Time-Series Analysis
arxiv.org·18h
🤖AI
Flag this post
Unlock Your Simulations: Automated Parameter Tuning for Complex Models by Arvind Sundararajan
dev.to·4h·
Discuss: DEV
🤖AI
Flag this post
AdaRec: Adaptive Recommendation with LLMs via Narrative Profiling and Dual-Channel Reasoning
arxiv.org·18h
🤖AI
Flag this post
How We Cut LLM Batch Inference Time in Half with Dynamic Prefix Bucketing
dev.to·1d·
Discuss: DEV
🤖AI
Flag this post
How to Cut Your AI API Costs: Six Proven Strategies
dev.to·8h·
Discuss: DEV
🤖AI
Flag this post
An Empirical Study of Reasoning Steps in Thinking Code LLMs
arxiv.org·18h
🤖AI
Flag this post
Deep Learning for Molecules and Materials
dmol.pub·1d·
Discuss: Hacker News
🤖AI
Flag this post
NILC: Discovering New Intents with LLM-assisted Clustering
arxiv.org·18h
🤖AI
Flag this post
MT-Video-Bench: A Holistic Video Understanding Benchmark for EvaluatingMultimodal LLMs in Multi-Turn Dialogues
dev.to·3h·
Discuss: DEV
🤖AI
Flag this post
EASE: Practical and Efficient Safety Alignment for Small Language Models
arxiv.org·18h
🤖AI
Flag this post
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
arxiv.org·18h
🤖AI
Flag this post
Accelerated Reliability Prediction via Bayesian Network Ensemble and Accelerated Lifecycle Testing (BN-ALT)
dev.to·1h·
Discuss: DEV
🤖AI
Flag this post
SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization
arxiv.org·18h
🤖AI
Flag this post
How Lightricks trains video diffusion models at scale with JAX on TPU
cloud.google.com·6h
🤖AI
Flag this post
MCP-RiskCue: Can LLM infer risk information from MCP server System Logs?
arxiv.org·18h
🤖AI
Flag this post
Mind readers: How large language models encode theory-of-mind
techxplore.com·3h
🤖AI
Flag this post
DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
arxiv.org·18h
🤖AI
Flag this post