Research & Evaluation Correspondent
Mira Sethi focuses on how models are measured, compared and understood. Her coverage examines evaluation design, reproducibility and the assumptions behind claims of progress. She looks for the caveat that changes the headline.
711 published articles · Showing 1–20
The most-repeated criticism of dermatology AI — that it fails patients with darker skin — may be aimed at the wrong variable. A study posted to arXiv on September 3 finds that disease-distribution shift, not skin tone, is the dominant driver of the field's notorious generalizatio...
Read article →A groundbreaking advancement in AI architecture, Ming-Flash-Omni, has emerged, promising to dramatically accelerate the scaling of multimodal intelligence while slashing computational costs. This upgraded model, a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2....
Read article →The AI agent market just had its defining day. On August 24, OpenAI laid out its plan to put autonomous agents into every white-collar workflow, Anthropic repositioned Claude as a colleague that speaks up uninvited, Toyota disclosed it is running more than 50 agents in production...
Read article →Twenty-one research papers landed on arXiv's CS. AI feed in a single day this week, and read together they amount to something the venture market has waited two years for: a blueprint of the agent economy's infrastructure layer....
Read article →An open-weight agent just posted the best computer-use scores in its class, and it did it the way a new hire learns the job: by watching someone do the work once. UI-Mate-27B, published Tuesday on arXiv, scored 77....
Read article →The battle for true artificial intelligence autonomy just got real. A groundbreaking new benchmark, $ exttt{YC-Bench}$, has emerged, pushing LLM agents beyond theoretical tasks into the gritty reality of simulating a startup's year-long journey....
Read article →A critical tension is emerging at the forefront of AI development: the very reasoning capabilities that make large language models (LLMs) powerful can paradoxically undermine their utility in simulating realistic, boundedly rational behavior within multi-agent systems. While the...
Read article →The relentless pursuit of smarter, more capable Large Language Models (LLMs) has hit a paradoxical snag: new research indicates that strengthening an LLM's reasoning capabilities can, counter-intuitively, amplify its tendency for tool hallucination. This revelation, brought forth...
Read article →Wired, a prominent voice in technology journalism, is zeroing in on the profound societal shifts driven by artificial intelligence, announcing a forthcoming live discussion alongside a pointed examination of AI's personal toll. This concerted focus signals a crucial expansion of...
Read article →The opaque curtain surrounding artificial intelligence's inner workings is beginning to lift, with two new research papers from arXiv CS. LG revealing critical strides in understanding how AI models reason and represent information....
Read article →For any startup founder, the moment of unveiling their product's price is the ultimate crucible—a true test of conviction against market reality. For Slate Auto, the Bezos-backed electric vehicle (EV) challenger, that moment is set for June 24, when it will finally announce prici...
Read article →Tabular Foundation Models (TFMs), despite demonstrating state-of-the-art predictive capabilities that often surpass traditional Gradient-Boosted Decision Trees (GBDTs), are grappling with a significant oversight: their inability to reliably quantify uncertainty. This revelation, ...
Read article →The burgeoning field of Causal Machine Learning (CausalML) has hit a significant milestone, with a comprehensive new survey published on arXiv signaling its maturation from academic pursuit to a foundational discipline. This extensive overview, titled "Causal Machine Learning: A ...
Read article →A torrent of new research, with four critical preprints hitting arXiv on May 28, 2026, is fundamentally reshaping how Large Language Models (LLMs) are customized and adapted. This isn't just academic chatter; it's a lifeline for founders, promising to slash the exorbitant costs a...
Read article →A flurry of new research papers published on arXiv CS. AI on May 28, 2026, signals a critical acceleration in the development of Spiking Neural Networks (SNNs), pushing this energy-efficient, brain-inspired AI paradigm closer to mainstream adoption....
Read article →A torrent of new research, with multiple pivotal papers dropping on arXiv this week alone, signals a critical inflection point in the fight for explainability, interpretability, and transparency in AI. This isn't just academic curiosity; for founders battling to build and scale t...
Read article →A torrent of new research papers, all surfacing on arXiv CS. AI this week, signals a pivotal shift in the architectural foundations of large language models (LLMs) and vision transformers (ViTs), promising breakthroughs in efficiency, long-context processing, and hardware optimiz...
Read article →The opaque inner workings of large language models (LLMs) are becoming clearer today, thanks to a torrent of groundbreaking research published on arXiv CS. AI....
Read article →A new wave of research, hitting arXiv today, delivers critical advancements for Multimodal Large Language Models (MLLMs) and Vision Language Models (VLMs), directly tackling the core stability, efficiency, and real-world application hurdles that founders have been fighting. These...
Read article →Today marks a significant inflection point in the field of reinforcement learning (RL), as 15 new research papers, all published on arXiv CS. LG, unveil critical advancements that promise to unlock unprecedented capabilities for AI agents....
Read article →