GPT-6 Astra beat the puzzle game Portal entirely on its own in about 24 hours, with zero human help after the initial goal was set. Developer cozyblaze…
Enhancing Multimodal Emotion Recognition via Multi-Feature Encoding and Attention-Based Fusion
arXiv:2609.04690v1 Announce Type: cross Abstract: Multimodal emotion recognition has attracted growing interest due to its importance in human-computer…
AI News Brief Hourly Summary 2026-09-07 20h : 13 posts
13 posts published in the last hour 17:32PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning 17:32Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics 17:32Dual-Part Multi-Lateral Branched Network for Multi-Class Segmentation in Cardiovascular Catheterization Angiograms 17:32Training-Free Halving of…
PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning
arXiv:2609.04598v1 Announce Type: cross Abstract: We introduce PetQA, a Korean long-form question-answering (QA) benchmark for evaluating veterinary…
Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics
arXiv:2609.04570v1 Announce Type: cross Abstract: LLM-based code generation fails when correctness depends on execution-dependent coupling: the meaning of…
Dual-Part Multi-Lateral Branched Network for Multi-Class Segmentation in Cardiovascular Catheterization Angiograms
arXiv:2609.04590v1 Announce Type: cross Abstract: Catheterisation image processing requires segmentation models that are fast, accurate and explainable.…
Training-Free Halving of Activated Experts in Fine-Grained Mixture-of-Experts Models
arXiv:2609.04575v1 Announce Type: cross Abstract: Modern fine-grained Mixture-of-Experts (MoE) models route each token to a small number of experts and…
When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models
arXiv:2609.04582v1 Announce Type: cross Abstract: A 0.6B language model, asked to verify 1,200 logical conclusions (half valid, half corrupted by a single…
Pitch-class Steering for Diffusion-based Music Generation via Latent-space Probes
arXiv:2609.04516v1 Announce Type: cross Abstract: Recent work on controllable music generation has focused on autoregressive models, leaving…
Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters
arXiv:2609.04513v1 Announce Type: cross Abstract: Compound AI workflows are increasingly used to serve complex AI tasks by coordinating multiple AI models…
A Semantic Model of Genetic Evidence: A Step Toward Bridging the Basic-Science-Clinic Gap
arXiv:2609.04509v1 Announce Type: cross Abstract: Scientific and clinical decision-making depends on evidence from the primary literature, but existing…
ChatGPT claws back web traffic share to 55.5 percent as Gemini’s brief comeback fades
ChatGPT has pushed its share of AI chatbot website traffic back up to 55.5 percent, according to Similarweb. Year-over-year, though, its lead shrank…
Continual Field-Adaptive Models (CFAMs) for Post-Deployment Physical AI
arXiv:2609.04552v1 Announce Type: cross Abstract: Unattended interactive autonomy – machines that step into danger in place of humans and complete tasks…
AI-designed drug appears to turn back the body’s biological clock in early trial
A study in Nature Biotechnology suggests that rentosertib, a drug designed with AI by Insilico Medicine, may reverse markers of biological aging. Six…
Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection
arXiv:2609.04533v1 Announce Type: cross Abstract: Prompt injection is widely recognized as a major security threat to AI agents that interact with…
AI News Brief Hourly Summary 2026-09-07 19h : 13 posts
13 posts published in the last hour 16:54Daily Roundup 16:32Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention Perspective 16:32Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation 16:32Shared circuits predict whether LLMs generalize across…
Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention Perspective
arXiv:2609.04489v1 Announce Type: cross Abstract: Pause-token methods improve LLM reasoning by inserting special tokens into sequences. Prior work…
Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation
arXiv:2609.04484v1 Announce Type: cross Abstract: This paper investigates structural priming in language model (LM) production, examining how preceding…