Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning
arxiv.org·3h
🏆LLM Benchmarking
Echo State Transformer: When chaos brings memory
arxiv.org·3h
🗜️Zstd
Tractable Representation Learning with Probabilistic Circuits
arxiv.org·3h
🔢BitNet Inference
Using a Framework Desktop for local AI
frame.work·11h
🤖AI
Using a Framework Desktop for local AI
frame.work·12h
🤖AI
Weight‑Generative Tuning for Multi‑Faceted Efficient Adaptation of Large Models
icml.cc·10h·
Discuss: Hacker News
📱Edge AI Optimization
INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling
arxiv.org·3h
🔍AI Interpretability
LLaDA 1.5: Variance-Reduced Preference Optimization for Diffusion LLMs
ml-gsai.github.io·5h·
Discuss: Hacker News
📊Embeddings
Boosting Temporal Sentence Grounding via Causal Inference
arxiv.org·3h
🧠Inference Serving
PRIME: Large Language Model Personalization with Cognitive Memory and Thought Processes
arxiv.org·3h
👤Search Personalization
Controlling Thinking Speed in Reasoning Models
arxiv.org·3h
🪄Prompt Engineering
How Much Content Do LLMs Generate That Induces Cognitive Bias in Users?
arxiv.org·3h
📋Text Quality
Economics of Claude 3 Opus Inference
lesswrong.com·13h
📊Model Serving Economics
Distilling High Diagnostic Value Patches for Whole Slide Image Classification Using Attention Mechanism
arxiv.org·3h
📊Embeddings
Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation
arxiv.org·3h
📊Embeddings
How a big shift in training LLMs led to a capability explosion
arstechnica.com·20h·
Discuss: Hacker News
🆕New AI
PB-LLMs: Privacy- and Bias-aware NLP Models using Named-Entity Recognition
arxiv.org·3h
🎛️Feed Filtering
Dissecting Clinical Reasoning in Language Models: A Comparative Study of Prompts and Model Adaptation Strategies
arxiv.org·3h
🪄Prompt Engineering
Spatio-Temporal LLM: Reasoning about Environments and Actions
arxiv.org·3h
🏆LLM Benchmarking
Latent Thermodynamic Flows: Unified Representation Learning and Generative Modeling of Temperature-Dependent Behaviors from Limited Data
arxiv.org·3h
🕯️Candle