arXiv:2603.21877v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but suffers from advantage collapse on “hard samples” where all rollouts fail. This lack of variance eliminates crucial learning signals. For these intractable samples, simply scaling up rollout budgets offers limited gains. We introduce Joint Policy and Prompt […]
Mochi: Aligning Pre-training and Inference for Efficient Graph Foundation Models via Meta-Learning
arXiv:2604.22031v2 Announce Type: replace-cross Abstract: We propose Mochi, a Graph Foundation Model that addresses task unification and training efficiency by adopting a meta-learning based training framework. Prior models pre-train with reconstruction-based objectives such as link prediction, and assume that the resulting representations can be aligned with downstream tasks through a separate unification step such as […]
HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization
arXiv:2605.03562v2 Announce Type: replace-cross Abstract: KV-cache quantizers usually optimize storage-space reconstruction, even though attention reads keys through logits and values through attention-weighted readout. We argue that persistent cache error should be measured in model-visible coordinates. For keys, the visible object is score error modulo constant shifts; this yields HeadQ, a key-side method that stores a […]
What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis
arXiv:2605.03354v2 Announce Type: replace Abstract: Agent memory failures are silent: an LLM-based agent can produce a fluent response even when it fails to extract, retain, or retrieve the information needed across sessions. The write-manage-read loop describes the external pipeline of these systems but leaves open which internal computations implement each stage. Tracing feature circuits across […]
Odyssey raises more than $300M as biotech goes public in IPO
Odyssey Therapeutics pulled together $279 million from its initial public offering, the autoimmune disease drug developer said Thursday night. With its IPO now priced, Odyssey is slated to begin trading on the Nasdaq on Friday …
Open-Rosalind: Tool-First Biomedical LLM Agents with Process-Aware Benchmarking
Large language models are increasingly used as scientific agents, yet the flexibility that benefits general-purpose agents can conflict with the accountability required in biomedical research. We study whether biomedical agents can be organized around auditable constraints rather than unconstrained autonomy. We present Open-Rosalind, a tool-first bio-agent system designed around four operational principles: evidence-grounded outputs, trace […]
Deep learning models for acute kidney injury prediction: multi-center external validation and evaluation under simulated continuous monitoring conditions
npj Digital Medicine, Published online: 08 May 2026; doi:10.1038/s41746-026-02722-2 Deep learning models for acute kidney injury prediction: multi-center external validation and evaluation under simulated continuous monitoring conditions
Bridging survival analysis and machine learning to improve healthy life expectancy estimation using PHR records
npj Digital Medicine, Published online: 08 May 2026; doi:10.1038/s41746-026-02700-8 Bridging survival analysis and machine learning to improve healthy life expectancy estimation using PHR records
Framework for artificial intelligence implementation research in healthcare: synthesizing current evidence on barriers and facilitators
npj Digital Medicine, Published online: 08 May 2026; doi:10.1038/s41746-026-02705-3 Framework for artificial intelligence implementation research in healthcare: synthesizing current evidence on barriers and facilitators
HES3-dependent regulatory functions in development and fusion-positive rhabdomyosarcoma
HES3/Her3 is a transcription factor that functions in non-canonical STAT3 signaling to promote the renewal of neural stem cells and has roles in multiple cancer contexts. To study its role in development and disease, we previously generated a CRISPR/Cas9 zebrafish knockout of her3, the ortholog to human HES3. HES3 is also a cooperating gene in […]
Variable transmission efficiency of mammalian origin HPAI D1.1 H5N1 strains in ferrets
Highly pathogenic avian influenza H5N1 2.3.4.4b genotype D1.1 lineage continues to predominate in the United States wild bird population and has spilled over into dairy cattle three independent times. To assess the transmission risk of this sublineage, we performed direct-contact transmission experiments for three distinct D1.1 strains in ferrets. Two of these strains were isolated […]
PromptBio-Bench: Benchmarking LLM-based Bioinformatics Agents for End-to-End Data Analysis
Large language model (LLM)-based agents hold transformative potential for automating bioinformatics workflows; however, systematic evaluations of their capabilities remain limited, hindering a clear assessment of their readiness for real-world application. We introduce PromptBio-Bench, a comprehensive evaluation suite of 194 expert-curated tasks spanning bioinformatics and data science at varied difficulty levels, and an evaluation framework for […]