Repository-level software engineering (SWE) comprises heterogeneous task categories, whose progress under pooled agentic reinforcement learning can be uneven: gains in some categories coincide with regressions in others, while aggregate resolution obscures these changes.…

arXiv

Sep 20

If You Hear It, Help Find It: Orthogonal Knowledge Distillation for Open-Vocabulary Audio-Visual Event Localization

Open-vocabulary audio-visual event localization (OV-AVEL) grounds a text-queried event in time from video, audio, and language. The supervision sources available to this task can differ in temporal-boundary reliability: on OV-AVEBench, our configured visual teacher gives more…

arXiv

Sep 20

The Evidence Ladder for Reinforcement Learning in Healthcare: From Retrospective Policies to Trusted Interventions

Reinforcement learning (RL) offers a natural language for healthcare decisions whose conse- quences unfold over time, yet most reported progress remains far from routine intervention. Ex- isting surveys organize the field by algorithm or clinical application. We instead review…

arXiv

Sep 20

Vision-Wireless Fusion for Multi-User Localization: A Cross-Modal Transformer Approach

Accurate multi-user localization is challenging in complex urban environments, where wireless measurements can become ambiguous under noise, blockage, and multipath, while visual observations provide complementary spatial context. This paper presents a vision-wireless fusion…

This week in Multimodal

This week

Get the morning digest

Today's trail

Red Hat expands NVIDIA tie-up on secure agentic AI

Lam Research beat earnings and raised guidance as chip bubble fears swirl

A regulation-aware architecture for governing AI-generated content

Pulse

MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering

deepseek-ai/DeepInfer

DeepInfer: High-performance inference framework for DeepSeek models

Blackstone’s Jas Khaira says fears over AI-buildout debt are overblown

Top picks

One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents

If You Hear It, Help Find It: Orthogonal Knowledge Distillation for Open-Vocabulary Audio-Visual Event Localization

The Evidence Ladder for Reinforcement Learning in Healthcare: From Retrospective Policies to Trusted Interventions

Vision-Wireless Fusion for Multi-User Localization: A Cross-Modal Transformer Approach

Today's trail

This week in Multimodal

Red Hat expands NVIDIA tie-up on secure agentic AI

Lam Research beat earnings and raised guidance as chip bubble fears swirl

A regulation-aware architecture for governing AI-generated content

Most active this week

Rising tools

MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering

deepseek-ai/DeepInfer

DeepInfer: High-performance inference framework for DeepSeek models

Blackstone’s Jas Khaira says fears over AI-buildout debt are overblown

deepseek-ai/DeepSeek-V4.1-Flash-1017

One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents

If You Hear It, Help Find It: Orthogonal Knowledge Distillation for Open-Vocabulary Audio-Visual Event Localization

The Evidence Ladder for Reinforcement Learning in Healthcare: From Retrospective Policies to Trusted Interventions

Vision-Wireless Fusion for Multi-User Localization: A Cross-Modal Transformer Approach