TraceSynth is a diffusion-based framework for generating synthetic kernel execution traces to augment limited real data for machine learning-based system diagnostics. It models traces as multi-channel sequences and applies constraint-guided repair to enforce system invariants. Experiments show that, for deterministic workloads, synthetic augmentation achieves up to 87.2% F1-Macro, with context length and constraint-guided repair significantly impacting quality. The approach reduces data collection costs while maintaining high performance for downstream tasks.
Why it matters: This work enables cost-effective augmentation of kernel traces in production observability pipelines, addressing runtime overhead, storage, and privacy constraints in industrial systems.
A new preprint on arXiv explores whether the acceptance and review effort of pull requests (PRs) can be predicted at the time of submission, before any reviewer discussion or CI feedback. Using the AIDev dataset, the authors show that tree-based machine learning models can predict PR acceptance with high accuracy (F1 scores above 0.95), but predicting review effort is much more challenging. The study finds that early PR models can help with triage, though review effort remains difficult to estimate from submission-time features alone.
Why it matters: This work provides early evidence that machine learning can assist maintainers in triaging both human- and AI-generated PRs, but highlights the limitations of automating review effort predictions.
Researchers introduce a two-agent neuro-symbolic framework for forecasting hand-foot-and-mouth disease (HFMD), combining an LLM-based Event Interpreter for contextual signals (such as school calendars, weather, and policy reports) with a probabilistic Forecast Generator. The system provides competitive accuracy compared to traditional and foundation models, while offering auditable explanations and robust 90% prediction intervals. Evaluations on Hong Kong and Lishui datasets show that LLM agents can integrate domain knowledge for interpretable public-health forecasts.
Why it matters: This work demonstrates that LLM agents can enhance the interpretability and trustworthiness of epidemiological forecasts by providing auditable rationales alongside predictions.
Anil Seth, a professor of cognitive and computational neuroscience, critiques recent research from Anthropic suggesting that its language model Claude may show signs of consciousness. Seth argues that such claims are exaggerated, likening them to confusing a simulation of a weather system with an actual hurricane. The article highlights the ongoing debate about the possibility of AI sentience.
Why it matters: This piece offers expert perspective on the contentious issue of AI consciousness, which has significant implications for AI safety and ethics.
Researchers present SLEUTH, a structured epistemic working memory system that enables language agents to explicitly track confirmed facts, active hypotheses, and open questions during multi-hop reasoning tasks. Evaluated on five multi-hop benchmarks, SLEUTH improves accuracy by up to 11 points on 4-hop chains and outperforms Reflexion without requiring multiple episodes. The study demonstrates that maintaining an organized epistemic state is crucial for scaling multi-hop reasoning, independent of raw model capability.
Why it matters: This work addresses the core challenge of context dilution in language agents and shows that structured reasoning organization, rather than model size alone, is key to reliable multi-step tool use.
A new preprint investigates the premise that quantization loss in large language models can be effectively predicted from per-layer sensitivities. The authors show that per-layer effects account for 85–93% of loss variance at 4-bit precision, and introduce a coverage model and additive predictor that achieve low KL divergence on models ranging from 30B to 355B parameters. Notably, their approach maintains performance on code and reasoning tasks below four bits, outperforming gradient-based methods in these regimes.
Why it matters: This work offers a theoretically grounded and empirically validated approach for mixed-precision quantization, potentially enabling more efficient deployment of large language models with minimal accuracy loss.
COMPASS introduces a method that uses empirical mobility scaling laws as feedback to guide large language model (LLM)-based human mobility simulation. By integrating population-level statistical regularities into the prompt construction process, COMPASS bridges the gap between individual trajectory realism and collective mobility patterns. The approach demonstrates improved performance over existing LLM-based simulators on two public datasets.
Why it matters: This work advances LLM-based geospatial simulation by enabling both realistic individual behaviors and accurate population-level mobility patterns, addressing a key limitation of prior methods.
Researchers present conDitar-dev, a conditional diffusion-based framework for structure-based drug design that generates ligands with strong binding affinities and improved ADMET properties. The model outperforms state-of-the-art baselines on a benchmark of human disease targets, achieving an average binding score of -8.85 kcal/mol and up to 73% improvement in ADMET properties. Experimental validation on PD-L1 and CSF1R targets yielded molecules with micromolar binding affinities and nanomolar IC50 values, demonstrating real-world applicability.
Why it matters: This work advances AI-driven drug discovery by demonstrating a method that generates molecules with both computational and experimental validation, potentially accelerating the development of new therapeutics.
A new study demonstrates that the widely used Gale-Shapley stable marriage algorithm is vulnerable to privacy attacks when the proposer side is malicious. The researchers show that, under these conditions, it is possible to recover the full preference lists of honest agents, including in real-world scenarios such as the National Resident Matching Program. The findings suggest that current implementations may expose sensitive information and highlight the need for privacy-preserving alternatives.
Why it matters: The results reveal critical privacy risks in matching algorithms used in sensitive applications, emphasizing the urgency for improved privacy protections.
A new study proposes a feature-guided zero-shot framework that leverages large language models (LLMs) for early chronic kidney disease (CKD) screening without the need for dataset-specific training. By selecting a compact set of clinically meaningful and readily available features, the researchers evaluated four LLMs across three heterogeneous CKD datasets from different countries. The models achieved consistent and statistically significant improvements in balanced accuracy and probability estimates, reaching performance levels suitable for screening purposes.
Why it matters: This work shows that LLMs can enable training-free, clinically meaningful CKD screening using minimal, community-accessible features, potentially improving access to screening in resource-limited settings.
Researchers have introduced JoPMol, a generative model that unifies gene expression profiles, molecular structure text, and chemical property data to enable precision molecular design. JoPMol demonstrates superior performance compared to state-of-the-art methods across several evaluation metrics and exhibits strong generalization in transfer tasks and biologically grounded simulations. The model's code is publicly available.
Why it matters: This work represents a notable advance in AI-driven drug discovery by enabling coordinated control over both biological and chemical conditions for personalized molecular design.
A new preprint systematically studies how the training duration of domain expert models affects the quality of merged multi-task models. The authors fine-tuned experts on five domains and three model sizes, evaluating five merging methods at various training checkpoints. They found that simple averaging performs worse as experts overfit, while sparsification-based merging methods achieve their best results well past the validation loss optimum. The study concludes that training duration and merging method should be selected together for optimal results.
Why it matters: This work provides actionable insights for practitioners seeking to improve multi-task model merging, a key technique for combining specialized models without co-training.
A new preprint introduces a white-box instrument based on hidden deterministic finite automata to separately measure reward attainment and latent-state learning in reinforcement learning (RL) agents. The study demonstrates that high reward does not necessarily indicate that an agent has learned the underlying task state, distinguishing between 'perception gaps' (where latent state is not recoverable from observations) and 'planning gaps' (where state is recoverable but not used). The authors show that optimizer strength, task structure, and observation informativeness each influence the relationship between reward and state learning.
Why it matters: This work challenges the common assumption that high reward in RL implies genuine task understanding, providing a method to diagnose when agents exploit shortcuts rather than learning true latent states.
CARE-LoRA is a method designed to reduce the memory bottleneck of activations during LoRA fine-tuning by replacing full input activations with low-rank compressed activations from the LoRA branch. It introduces a lightweight reconstruction matrix computed during the forward pass, enabling gradient reconstruction in backpropagation while keeping LoRA matrices fully trainable. Experiments across various models and tasks show that CARE-LoRA achieves competitive or superior performance compared to standard LoRA and its variants, with a substantially reduced memory footprint.
Why it matters: This approach addresses a major memory limitation in fine-tuning large models, potentially making such processes more feasible on hardware with limited memory.
Researchers present Support Vector Attention (SV-Attention), a novel max-margin memory mechanism for attention models that enables certified token eviction and exact unlearning. SV-Attention achieves higher rare-item recall (0.86 vs. 0.32) and better retention (0.80 vs. 0.05 deterioration hours) on MIMIC-IV data streams compared to baselines, and demonstrates improved compression (2.178 BPC vs. 2.383) on enwik8 relative to a sliding-window Transformer. The method also supports surgical forgetting, exact editing, and patient-record deletion in real-world scenarios.
Why it matters: This work introduces a principled and practical approach to certified unlearning in attention mechanisms, addressing a key challenge in machine learning privacy and data management.
A new training-free attribution method is introduced to analyze the dependencies of feedforward network (FFN) neurons in Transformer models. The study finds that small, sparse subsets of upstream activations and attention outputs can preserve neuron activations with high fidelity, even when other inputs are masked. This reveals that FFNs, despite their dense parameterization, have sparse and structured inter-layer dependencies at the neuron level. The method is scalable and can be used for circuit-level interpretability and identifying sparse pathways for potential efficiency gains.
Why it matters: This work offers a practical and scalable approach to understanding and potentially optimizing the internal structure of Transformer models, which could lead to more efficient inference and improved interpretability.
Researchers introduce the first pseudo-polynomial-time exact algorithm for computing Data Shapley values in weighted k-nearest-neighbor (KNN) regression, addressing a longstanding computational barrier. The work also presents a certified fully polynomial-time approximation scheme (FPTAS) with machine-checkable error bounds and extends the approach to soft-label multi-class prediction. An open-source implementation and the first exact ground-truth dataset for weighted-regression Data Shapley are provided.
Why it matters: This advance enables deterministic, certified data valuation in weighted KNN regression, providing a reliable reference for auditing and improving approximate methods.
A new preprint introduces an agentic AI scientific community composed of virtual laboratories that autonomously discover neural operator architectures. Each lab uses LLM agents for planning, training, and peer review, operating under a citation-based economy. The system demonstrates the ability to find high-accuracy, low-parameter-count neural operator designs across five PDE benchmark problems, outperforming rule-based alternatives in maintaining architectural diversity.
Why it matters: This work represents a significant advance in automating scientific discovery using LLM-driven agentic systems, highlighting the potential for AI to autonomously innovate in complex domains.
Airbnb has developed and deployed Proximity Features, a privacy-compliant system that addresses the cold-start personalization problem by grouping users based on geographic proximity using geo-IP data and adaptive clustering. This approach aggregates signals for groups of around 1,000 users, avoiding the need for persistent individual identifiers and operating within consent-gated privacy controls. Online A/B tests in production show statistically significant increases in bookings, particularly for users lacking recent or any history.
Why it matters: This work provides a scalable, privacy-preserving solution to cold-start personalization with demonstrated real-world impact at a major online platform.
Researchers introduce LiteTopK, a fused GPU kernel designed to accelerate Indexer-TopK operations in long-context sparse attention by leveraging the curse of dimensionality. LiteTopK samples data to estimate score ranges and partitions candidates into bins, reducing memory traffic and overhead while maintaining exact top-k correctness. Experiments show a 1.2x speedup in the prefill stage of GLM 5.2 during real-world deployment, along with lower memory usage.
Why it matters: This work offers a practical advance in the efficiency of sparse attention for large language models, enabling faster and more memory-efficient processing of long contexts.