The latest AI news, launches, models, companies and research — collected from official sources, research feeds and reporting, grouped into stories and ranked by the BharatHunt Trend Score.
Updated 2 minutes ago30 stories in the last 24 hours
456 stories
Studying Image Tokenizers as Visual Languages in Unified Multimodal Models. It centres on Multimodal, and also names Fine-tuning. Reported by arXiv. Bharat Hunt files it under AI Models and Computer Vision — the section covering a new or updated model, its capabilities, benchmarks or availability.
NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting. The story centres on Multimodal. Reported by arXiv. Bharat Hunt files it under AI Models — the section covering a new or updated model, its capabilities, benchmarks or availability.
Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation. The story centres on Benchmarks. Reported by arXiv. Bharat Hunt files it under AI Coding and AI Regulation — the section covering code generation, developer agents, IDEs and software engineering.
Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails. It centres on Fine-tuning, and also names Gemma and Meta. Reported by arXiv. Bharat Hunt files it under AI Models and AI Regulation — the section covering a new or updated model, its capabilities, benchmarks or availability.
ExecCritic: Learn to Test, Test to Improve for Coding Agents. It centres on Qwen, and also names GPT and Benchmarks. Reported by arXiv. Bharat Hunt files it under AI Coding and AI Models — the section covering code generation, developer agents, IDEs and software engineering.
A Generalization of Amari's Bayesian Duality. Reported by arXiv. Bharat Hunt files it under AI Models — the section covering a new or updated model, its capabilities, benchmarks or availability. Open the original report for the full detail.
DeCAL: Towards Physically-Grounded Dexterous Vision-Language-Action Models via Contact-Aware Latent Co-Imagination. It centres on Multimodal, and also names GitHub. Reported by arXiv. Bharat Hunt files it under AI Models and AI Regulation — the section covering a new or updated model, its capabilities, benchmarks or availability.
MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents. Reported by arXiv. Bharat Hunt files it under AI Models — the section covering a new or updated model, its capabilities, benchmarks or availability. Open the original report for the full detail.
SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research? It centres on AI Safety, and also names Gemma and Benchmarks. Reported by arXiv. Bharat Hunt files it under AI Research and AI Agents — the section covering papers, benchmarks, evaluations, interpretability and safety results.
The Surprising Effectiveness of Approximate Value Iteration in Self-Play. It centres on Benchmarks, and also names Inference. Reported by arXiv. Bharat Hunt files it under AI Tools — the section covering applications people use — assistants, editors, search, productivity.
Measuring LLM Sycophancy under Sustained Multi-Turn Pressure. The story centres on Benchmarks. Reported by arXiv. Bharat Hunt files it under AI Models — the section covering a new or updated model, its capabilities, benchmarks or availability. Open the original report for the full detail.
It's Not RoPE that Creates Sinks: The Role of Self-Concentration and Value-Non-Mixing in Attention. Reported by arXiv. Bharat Hunt files it under AI Research — the section covering papers, benchmarks, evaluations, interpretability and safety results. Open the original report for the full detail.
Bharat Hunt links to original reporting and does not republish it. Headlines and links belong to their publishers; summaries and the trend ranking are ours. All AI stories
Stories in the last 24 hours, against the 24 before it. A change is shown only where the earlier window had enough coverage to compare against.
Our own 0-100 ranking, not an industry metric and not anyone else’s “trending” number. It combines how recently a story was covered (32%), how many independent publications covered it (28%), how fast that coverage is arriving right now (20%), how reliable those sources are (12%) and how many people opened the story (8%).
A story we cannot date carries no score at all rather than a made-up one, so some cards show no badge. Summaries are written by Bharat Hunt from the headline and the coverage — the original article is always the source of truth, and every link goes to the publisher.