🧠

AI

13,488 AI articles curated from 50+ sources with AI-powered sentiment analysis, importance scoring, and key takeaways.

13488 articles

AIBullisharXiv – CS AI · Apr 294/10

🧠

Large Language Models Explore by Latent Distilling

AIBullisharXiv – CS AI · Apr 294/10

🧠

Rethinking Layer Redundancy in Large Language Models: Calibration Objectives and Search for Depth Pruning

🏢 Perplexity

AIBullisharXiv – CS AI · Apr 294/10

🧠

ADE: Adaptive Dictionary Embeddings -- Scaling Multi-Anchor Representations to Large Language Models

AIBullisharXiv – CS AI · Apr 294/10

🧠

Compute Aligned Training: Optimizing for Test Time Inference

AIBullisharXiv – CS AI · Apr 294/10

🧠

Faithful Autoformalization via Roundtrip Verification and Repair

🧠 GPT-5🧠 Claude🧠 Opus

AIBullisharXiv – CS AI · Apr 294/10

🧠

Dual-Track CoT: Budget-Aware Stepwise Guidance for Small LMs

AIBullisharXiv – CS AI · Apr 294/10

🧠

Analyzing LLM Reasoning to Uncover Mental Health Stigma

AIBullisharXiv – CS AI · Apr 294/10

🧠

Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver

🧠 GPT-5🧠 Claude🧠 Opus

AIBullisharXiv – CS AI · Apr 294/10

🧠

M$^3$-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering

AIBullisharXiv – CS AI · Apr 294/10

🧠

Frictive Policy Optimization for LLMs: Epistemic Intervention, Risk-Sensitive Control, and Reflective Alignment

AIBullisharXiv – CS AI · Apr 294/10

🧠

The Role of Symmetry in Optimizing Overparameterized Networks

AIBullisharXiv – CS AI · Apr 294/10

🧠

Making AI-Assisted Grant Evaluation Auditable without Exposing the Model

🏢 Meta

AIBullisharXiv – CS AI · Apr 294/10

🧠

Below-Chance Blindness: Prompted Underperformance in Small LLMs Produces Positional Bias Rather than Answer Avoidance

🧠 Llama

AINeutralarXiv – CS AI · Apr 294/10

🧠

LegalMidm: Use-Case-Driven Legal Domain Specialization for Korean Large Language Model

AIBullisharXiv – CS AI · Apr 294/10

🧠

Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models

AIBullisharXiv – CS AI · Apr 294/10

🧠

AHASD: Asynchronous Heterogeneous Architecture for LLM Adaptive Drafting Speculative Decoding on Mobile Devices

AIBullisharXiv – CS AI · Apr 294/10

🧠

VAE-Inf: A statistically interpretable generative paradigm for imbalanced classification

AIBullisharXiv – CS AI · Apr 294/10

🧠

A Faceted Proposal for Transparent Attribution of AI-Assisted Text Production

AIBullisharXiv – CS AI · Apr 294/10

🧠

The Structured Output Benchmark: A Multi-Source Benchmark for Evaluating Structured Output Quality in Large Language Models

🏢 Meta

AIBullisharXiv – CS AI · Apr 294/10

🧠

Safe-Support Q-Learning: Learning without Unsafe Exploration

AIBullisharXiv – CS AI · Apr 294/10

🧠

ML-SAN: Multi-Level Speaker-Adaptive Network for Emotion Recognition in Conversations

AIBullisharXiv – CS AI · Apr 294/10

🧠

FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices

🏢 Nvidia

AIBullisharXiv – CS AI · Apr 294/10

🧠

An Investigation of Linguistic Biases in LLM-Based Recommendations

AIBullisharXiv – CS AI · Apr 294/10

🧠

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing

AIBullisharXiv – CS AI · Apr 294/10

🧠

From World-Gen to Quest-Line: A Dependency-Driven Prompt Pipeline for Coherent RPG Generation

← PrevPage 319 of 540Next →