Latest in AI and developer tools

Today's trail

updated just now

Pulse · msn.com

msn.com · Nov 13

World's first compute-in-memory AI chip for headphones lands in Japan with Soundcore Space 2 Pro

Soundcore Space 2 Pro launches in Japan carrying the world's first Compute-in-Memory AI chip in a consumer wearable. Anker's Thus chip eliminates the Von Neumann energy bottleneck, enabling eight-microphone Adaptive ANC 3.

Pulse

Top picks this weekarXiv

arXiv

Nov 11

Learning a calibrated decision head from logged bandit feedback

A decision head reads a state and a list of options and returns a probability per option in one forward pass. Once deployed, it usually observes only whether the option it chose was right: logged bandit feedback. We adapt such a head, LoRA on Qwen3-0.6B-Base and 1.7B-Base, from that feedback and report three results. First, the Brier or log score of the sampled action's own probability is not a usable REINFORCE reward: every wrong action earns at least gold's reward, with a mean baseline the lowest-probability wrong action gets the largest advantage, and at two options the signal is zero; in one run it cut accuracy on ordered-scale questions from .636 to .111. Scoring the probability as a loss by the pathwise gradient avoids the collapse, as do the REINFORCE rewards r and r minus p. Second, with full labels, none of four tested bandit arms beat cross-entropy plus one temperature on mean expected calibration error (ECE) over four unseen label schemas. Third, from logged feedback alone, Chosen-Action Proper Scoring (CAPS), the direct method with a proper score on the chosen action's probability, beats fine-tuning on confirmed answers only, which discards negatives: on Banking77 by…

Top picks

All arXiv Hugging Face GitHub Hacker News

Latest Top this week

arXiv

Sep 20

Automated Evaluation of Multi-Turn Dialogues in In-Car Conversational Assistants

In-car conversational assistants (ICAs) are increasingly integrated into vehicles to support route planning, vehicle control, and information access. Ensuring their reliability is challenging due to multi-turn interactions, the absence of explicit ground truth, and strict…

arXiv

Sep 20

GAPS: Generative Active Pseudo-view Selection for Sparse-View 3D Gaussian Splatting

Novel view synthesis from sparse observations is severely under-constrained. Although 3D Gaussian Splatting (3DGS) enables real-time rendering, it produces floaters, broken geometry, and washed-out backgrounds when trained with few views. We propose an alternating optimization…

arXiv

Sep 20

Tool-Augmented On-Policy Distillation for LLM Domain Adaptation in Sequence-Based Omics Tasks

Multi-omics sequences contain complex biological patterns, yet deciphering their mechanisms for automated scientific discovery remains challenging. As large language models (LLMs) interpret these sequences, evaluating both predictions and scientific reasoning is critical.…

arXiv

Sep 20

Dynamical low-rank equilibrium computation for stochastic games between advanced persistent threats and moving target defense

Moving target defense (MTD) against advanced persistent threats (APTs) in industrial control systems (ICS) has well-established game-theoretic formulations, but their practical value hinges on equilibrium computation, which faces two gaps: full-rank value iteration is…

This week in Multimodal

This week

Get the morning digest

Today's trail

Pulse

Top picks

Today's trail

Rising tools

Most active this week

This week in Multimodal