Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error
arxiv.org·4d
🧠Large Language Models (LLMs)
Flag this post
The Riddle of Reflection: Evaluating Reasoning and Self-Awareness in Multilingual LLMs using Indian Riddles
arxiv.org·21h
🧠Large Language Models (LLMs)
Flag this post
Tackling the Kidnapped Robot Problem via Sparse Feasible Hypothesis Sampling and Reliable Batched Multi-Stage Inference
arxiv.org·21h
⚡Real-time AI Systems
Flag this post
Towards Sub-millisecond Latency and Guaranteed Bit Rates in 5G User Plane
arxiv.org·21h
🔧Systems-level optimizations for LLM serving
Flag this post
QuantumBench: A Benchmark for Quantum Problem Solving
arxiv.org·21h
🧠Large Language Models (LLMs)
Flag this post
Real-DRL: Teach and Learn in Reality
arxiv.org·21h
⚡Real-time AI Systems
Flag this post
Can SAEs reveal and mitigate racial biases of LLMs in healthcare?
arxiv.org·21h
🧠Large Language Models (LLMs)
Flag this post
Calibration Across Layers: Understanding Calibration Evolution in LLMs
arxiv.org·21h
🧠Large Language Models (LLMs)
Flag this post
Feature-Guided SAE Steering for Refusal-Rate Control using Contrasting Prompts
arxiv.org·21h
💬Prompt optimizations for LLM serving
Flag this post
A Multi-agent Large Language Model Framework to Automatically Assess Performance of a Clinical AI Triage Tool
arxiv.org·4d
📊AI Performance Profiling
Flag this post
Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search
arxiv.org·4d
💬Prompt optimizations for LLM serving
Flag this post
Computation as a Game
arxiv.org·21h
💬Prompt optimizations for LLM serving
Flag this post
FLoRA: Fused forward-backward adapters for parameter efficient fine-tuning and reducing inference-time latencies of LLMs
arxiv.org·21h
🧠Large Language Models (LLMs)
Flag this post
Beyond Single-Tokenomics: How Farcaster's Pluralistic Incentives Reshape Social Networking
arxiv.org·21h
🧠Large Language Models (LLMs)
Flag this post
Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward
arxiv.org·21h
🔍Retrieval-augmented generation
Flag this post
RailEstate: An Interactive System for Metro Linked Property Trends
arxiv.org·21h
🧠Large Language Models (LLMs)
Flag this post
Inferring multiple helper Dafny assertions with LLMs
arxiv.org·21h
🔧Systems-level optimizations for LLM serving
Flag this post
A Systematic Literature Review of Code Hallucinations in LLMs: Characterization, Mitigation Methods, Challenges, and Future Directions for Reliable AI
arxiv.org·21h
💬Prompt optimizations for LLM serving
Flag this post
Engineering.ai: A Platform for Teams of AI Engineers in Computational Design
arxiv.org·21h
⚙️AI Infrastructure Automation
Flag this post
STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack
arxiv.org·21h
🧠Large Language Models (LLMs)
Flag this post