Latest in AI and developer tools

Today's trail

updated 23m ago

Last hour Today

Pulse · freep.com

freep.com · Nov 3

Labarna AI Releases Two Films on Its 60-Day Build Model: MVP in Production on Day 30, Full Handover on Day 60

Pulse · cnbc.com

cnbc.com · Nov 3

Lovable CEO says AI is collapsing barriers to starting a business

Lovable CEO says AI is collapsing barriers to starting a business Lovable CEO Anton Osika joins Arjun Kharpal to discuss how AI is making it easier to build apps, start businesses and turn ideas into products. They explore vibe coding, AI agents, the future of developers and whether Europe can compete in the global AI race. 35:37 3 minutes ago Arjun Kharpal

Pulse

Top picks this weekarXiv

arXiv

Nov 2

Whitened Advantage Summation Policy Optimization: Correlation-Aware Aggregation for Multi-Reward Reinforcement Learning

Reinforcement learning for language models often combines several rewards by normalizing each one and adding them with fixed weights. When the rewards are correlated, the variation they share is counted once for every reward that carries it. In terms of the ZCA-decorrelated components of the reward signal, the weighted sum applies weights $Σ^{1/2} w$ rather than the chosen weights $w$, where $Σ$ is the reward correlation matrix. We study WAS-PO, which whitens the normalized advantages with $Σ^{-1/2}$ before adding them, so that the chosen weights apply to those components. We derive the scalarized objective whose gradient it follows when normalization statistics are held fixed, show that its weights on the raw rewards can be negative, give an exact two-reward condition under which the lighter-weighted reward is reversed, and give a loose bound on the error from estimating $Σ$ during training. On tool calling with Qwen2.5-1.5B-Instruct, WAS-PO reached a higher mean training reward than GDPO in all seven seeds with three rewards (3.8% higher) and all three seeds with four (3.9% higher). WAS-PO also replaces GDPO's per-prompt normalization with batch-level normalization, and we did…

Top picks

All arXiv Hugging Face GitHub Hacker News

Latest Top this week

arXiv

Sep 19

An Accurate and Interpretable Hyper Graph Neural Network for GBM Survival Prediction

Survival prediction for glioblastoma multiforme (GBM) demands models that are both accurate and interpretable, yet existing approaches treat these objectives as com- peting, where performant models sacrifice transparency, while interpretable models accept degraded predictive…

GitHub

Sep 19

alibaba/last-secure-code-benchmark

Shell repository · 133 stars

Merge++: Universal Merge Refinement Through Data-Free Checkpoint Inversion

Model merging consolidates fine-tuned experts into one multi-task model without retraining. All existing data-free methods approach this problem entirely in weight space. Restricted to arithmetic on parameters, these methods never observe how each expert behaves, a signal that…

arXiv

Sep 19

Block-Sparse Attention with Semantic-Geometric Decoupled Routing

Long-context inference has become a defining capability of large language models, but exact dense attention remains costly due to its quadratic scaling with sequence length. Block-sparse attention offers a hardware-friendly alternative by routing each query block to a small set…

This week in Multimodal

This week

Get the morning digest

Today's trail

Pulse

Top picks

Today's trail

This week in Multimodal

Most active this week

Rising tools