📄 Research AI News
Feed for best AI research releases, updates and latest AI research news.
- Forecasting viral evolution from phylogenetic trees
Viral mutation forecasting plays a key role in pandemic preparedness by enabling researchers to anticipate novel variants and design proactive interventions. Evolutionary histories, represented as phylogenetic trees, offer key insights into the emergence of past and present strains, yet their role in predicting future sequence changes remains largely unexplored. We introduce antiGen, a machine learning model that forecasts the evolutionary future of viruses by learning from their evolutionary past. antiGen achieves state-of-the-art performance for predicting mutations to the SARS-CoV-2 spike protein, anticipating never-before-seen mutations and mutations that emerge years after the model's training window. antiGen-forecasted spike mutations also retain pseudoviral infectivity in vitro. Moreover, antiGen demonstrates leading predictive performance on surface proteins of influenza virus, respiratory syncytial virus, and dengue virus despite far less available sequencing data. Viral evolution models that explicitly learn from phylogenetic structure offer a valuable resource for applications ranging from epidemiological modeling to therapeutic development.
- Skin Cancer Classification Using Explainable Artificial Intelligence With an Ensemble Model and Rigorous Leakage Free Validation
Background: Reliable melanoma classification requires models that capture both local dermoscopic morphology and broader contextual patterns while maintaining auditable, leakageaware internal validation. Objectives: To develop and internally validate an EfficientNetB0-Swin Transformer Tiny ensemble for classifying histopathologically verified dermoscopic images as benign melanocytic lesions or malignant melanoma. Methods: This retrospective diagnostic model-development and internal validation study screened 552,869 ISIC Archive records; filtering and dermatologist review yielded 1,199 uniquepatient and unique lesion images (578 benign and 621 malignant). Images were the predictors and histopathology was the reference. ImageNet pretrained EfficientNetB0 and Swin-T features were fused. Patient independent five fold validation used weighted sampling, mixup, label smoothing, AdamW, early stopping, and five view test time augmentation. Results: Mean accuracy was 0.89325 {+/-} 0.03179, mean receiver operating characteristic area under the curve (ROC-AUC) was 0.96348 {+/-} 0.01695, and mean support weighted F1-score was 0.89300 {+/-} 0.03220. The fold level 95% confidence intervals were 0.8538-0.9327 for accuracy and 0.9424-0.9845 for ROC-AUC. Pooled counts were 526 true negatives, 52 false positives, 76 false negatives, and 545 true positives, yielding 87.76% sensitivity and 91.00% specificity. Qualitative Grad-CAM review showed peripheral artifact activation in two false positives and lesion centered activation in two correctly classified cases; these observations were not systematically scored. Limitations: The validation folds were also used for early stopping and checkpoint selection. Device stratified analysis, systematic interpretability scoring, calibration, and independent external validation were unavailable. Conclusions: The ensemble showed high internal discrimination and is intended only as a clinician facing adjunct. The error audit workflow enables targeted retrospective review, but external validation is required before clinical use or generalizability claims.
- Post-Training Language Models for Gold-Medal Performance in Coding Competitions
Competitive programming has become a key test of large language model reasoning, with international competitions such as IOI and ICPC representing its most challenging settings. We present an end-to-end specialization pipeline combining large-scale problem curation, synthetic reasoning traces, super...
- AI Contextual Measurement for Recovering Individual and Group-Level Effects: Validation Against Survey Measures and an Occupational Application
Researchers increasingly use artificial intelligence to construct measures of social, organizational, and occupational characteristics that are absent from conventional surveys. We propose AICOME, AI COntextual MEasurement, a framework for evaluating whether AI-derived respondent-level measures can ...
- Large Language Models (LLMs) for Telecom Root Cause Analysis (RCA): A Structured Reasoning Framework for Evidence-Grounded Diagnosis
Root cause analysis (RCA) is a critical task in telecom network operations, but diagnosing performance degradations in modern 5G and emerging 6G networks remains challenging due to complex cross-layer dependencies. While large language models (LLMs) offer promising capabilities for reasoning and kno...
- SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment
The performance of LLM-based agents is jointly shaped by the base model and the harness used when interacting with the environment. This exposes them to safety risks in both harmful final responses and multi-step execution trajectories. Existing safety alignment mechanisms often rely on either exter...
- Untangling the Mechanisms of Misleading Context in Medical Question Answering
Large language models now answer medical questions with expert-level performance. However, the context these systems act on can be misleading, and misleading context can corrupt a model's medical judgment. To understand how misleading context corrupts this judgment, we examine the model's susceptibi...
- Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems
Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection. Despite strong empirical results, these systems lack a unified account of coordination, memory improvement, and the role of external verification. We model orch...
- DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models
RAG has become the de facto method for incorporating new, corpus-specific knowledge into an instruction following LLM (Instruct LLM). Although RAG-based prompting improves factual grounding, it fails when retrieval is incorrect or incomplete, leading to hallucinations. Finetuning methods such as RAF...
- From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs
When LLMs support public-facing or high-stakes workflows, missed fabrications can harm users and institutions, while false alarms consume limited human-review capacity. When no trusted context or reference document is available, we study two signals accessible through black-box model APIs: semantic ...
- Loom: Weaving Diagnostic Strands into Free-Text Consensus via Embedding-Space Reweighting
Aggregating noisy, conflicting textual hypotheses into a reliable consensus is a fundamental challenge when deploying NLP systems in real-world industrial settings. While monolithic Large Language Model (LLM) agents offer unbounded expressivity for tasks like Root Cause Analysis (RCA), they suffer f...
- TaRA: Training-Aware Low-Rank Adaptation Initialization
Low-Rank Adaptation (LoRA) has become a de facto standard for parameter-efficient fine-tuning (PEFT), yet its performance is highly sensitive to initialization due to the information bottleneck imposed by low-rank decomposition. Existing approaches attempt to construct high-quality LoRA initializati...
- Automated Vulnerability Injection in Smart Contracts Using Large Language Models
Assessing vulnerability detection tools for smart contracts requires datasets with known ground truth, yet such datasets are scarce and difficult to build by hand. We propose an approach that uses Large Language Models (LLMs) to automatically inject vulnerabilities into Solidity smart contracts, and...
- Competitive Market Behavior of LLMs
Large language models (LLMs) are increasingly deployed as economic agents, yet there is little evidence whether LLM agents are suited for participating in market mechanisms designed for humans, and whether these mechanisms deliver desired outcomes when faced with LLM agents. We address this question...
- ProbeMatchDTI: Probe-Driven Multi-Scale Biochemical Pattern Matching for Drug-Target Interaction Prediction
Drug-target interaction (DTI) prediction is an important task in AI-driven drug discovery. Although recent biochemical representation learning methods have improved DTI prediction, their passive feature aggregation tends to favor dominant molecular patterns while suppressing weak yet binding-relevan...
- Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs
Modern large language models (LLMs) rely on reinforcement learning to build strong capabilities in individual domains, but integrating those capabilities into a single deployable model remains challenging. By routing each sample to the teacher whose domain matches it, existing approaches let a domai...
- ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering
Document Visual Question Answering (DocVQA) often leverages Retrieval-Augmented Generation (RAG), where late-interaction encoders are commonly used to identify document pages relevant to a user query, before answer generation by a Large Vision-Language Model (LVLM). Existing approaches typically ret...
- CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI
We present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol (MCP). A single episode spans 300+ turns and produces thousands of tool calls over a large action space, requiring sustained planning, sta...
- Addressing Trust in AI Systems through Education: A Didactic Perspective
Machine learning (ML) education faces two persistent and connected obstacles: many educational tools present ML as an opaque black box, which leaves learners with a superficial understanding, and this same opacity prevents users from forming the calibrated trust that appropriate reliance on AI syste...
- UTP-Bench: Uncertainty-aware Travel Planning Benchmark
Large Language Models (LLMs) have recently demonstrated strong capabilities in automated travel itinerary generation. However, real- world travel planning is inherently uncertain: transportation delays, crowd fluctuations, and unexpected stochastic delays frequently inval- idate otherwise feasible s...
- PolERo: Studying Political Evasion in Romanian
Political evasion refers to responses that engage with a question while withholding the requested information. Recent NLP work frames political evasion as a classification task using a two-level taxonomy of response clarity and fine-grained evasion strategies. Existing work on response clarity and e...
- MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts
While existing work on LLM authorship attribution (AA) has made progress, available benchmarks remain limited, often focusing on English, controlled settings, or relatively outdated models, with the few multilingual studies considering only relatively short texts. We introduce MultiGhostBench, a mul...
- Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance
We study the dynamics of Stochastic Gradient Descent (SGD), which is known to steer deep neural networks toward invariant sets that correspond to simpler subnetworks. How this steering unfolds over time remains poorly understood. We answer this by modeling the stochastic gradient flow (SGF) as a per...
- Diagnosing with Insights: Structured Analysis of Agent Failures via Behavioral Abstractions
With the proliferation of LLM agents, the ability to understand and diagnose failures in agents is essential to achieving superior effectiveness and trustworthiness. As agent failures often manifest via long and complex trajectories, manually finding the needles in the haystack is untenable. However...
- Cliff: Learning Process Rewards from the First Mistake
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for large language model (LLM) post-training, but its reliance on coarse outcome rewards leads to limited guidance on intermediate reasoning processes. Existing approaches such as process reward modeling and on-...
- NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning
Named Entity Recognition (NER) has achieved substantial progress since the advent of large language models (LLMs). Nevertheless, the recognition of long-tail and domain-specific entities remains challenging due to the deficiency in parametric knowledge. Retrieval-augmented generation (RAG) offers a ...
- Discriminative World Models for Web Agents
Recent web agents use world models for test-time action selection by sampling candidate actions, predicting the resulting web states, and ranking them with a ranker model or a Process Reward Model (PRM). These world models are typically trained via supervised next-state prediction to generate fixed ...
- Dutch Books for Language Models
People increasingly use language models to support life decisions. Many such decisions involve a probabilistic forecast: How likely is a major life event, a natural disaster, or an economic outcome? Users of language models may implicitly trust that these forecasts fall out of a coherent world model...
- From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution
Training data attribution (TDA) aims to identify training examples that shape model behavior, but its intervention value depends on both which examples are selected and how they are modified. Influence functions (IF) estimate behavioral changes under infinitesimal reweighting, yet IF-selected exampl...
- Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents
On-premise assistants can give factory workers conversational access to machine documentation, but models capable of the task rarely fit shop-floor hardware. We show that after structural compression and retrieval-grounded adaptation, model size is no longer a reliable predictor of adapted answer qu...
- Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for planning, execution, memory, and verification, but this architecture still leaves domain-specific know-how outside the agent. We call this missing layer op...
- HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design
Polymeric materials are central to modern technologies, with applications ranging from energy to health and transportation. Although AI has made significant advances in materials discovery, the hierarchical structure of polymers across multiple length scales makes them inherently difficult to repres...
- Language Models Can Control Their Own Attention
Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to find the few tokens that matter. If the user asks about a previous detail in a 1M-token conversation, global attention layers must scan the full context to generate each token of the re...
- RVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucinations in Large Vision-Language Models
Large vision-language models have achieved remarkable success in vision-language tasks. However, they remain prone to Visual Hallucinations (VHs), undermining their reliability in real-world applications. Existing solutions typically require curated datasets, additional training, or multi-round deco...
- Door-in-the-Face Requests and Refusal Behaviour in Large Language Models
Does the door-in-the-face technique work on language models? In humans, a large request that is refused makes a smaller follow-up request more likely to be granted. We test this on nine production models from three providers: each model refuses a large request, then receives a smaller version of the...
- Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and Difference-Fusion Framework
Image enhancement and restoration have become standard back-end operations on short-video and social media platforms to boost UGC visual experience. Yet these processes inevitably introduce visual anomalies--especially in faces, texts, and textures--that directly undermine perceptual fidelity and vi...
- Spectral Initialization and Scheduled Graph Smoothness for Uncertain Knowledge Graph Completion
Uncertain knowledge graphs (UKGs) extend knowledge graphs by assigning each triple a continuous confidence score. Since most possible triples lack observed confidences, recent methods rely on semi-supervised learning to generate pseudo-labels. These methods initialize entity embeddings without using...
- Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models
Text-to-image (T2I) models have achieved remarkable success at faithfully rendering specified objects and attributes, yet their ability to produce visual metaphors, images that convey abstract ideas by combining elements from two distinct domains, remains largely unexamined. To bridge this gap, we i...
- RINSE: Robust Target-Time Normality Estimation for Zero-Shot Graph Anomaly Detection
Zero-shot graph anomaly detection seeks to deploy a detector trained on source graphs to unseen, unlabeled targets, yet domain shift can make source-derived notions of normality unreliable. We introduce RINSE (Robust Iterative Normality Self-Estimation), a gradient-free target-time framework that ke...
- DeepAffinity: Long-Term Aspect Preference Prediction in eCommerce using Small Language Models
We explore predicting eCommerce user preferences for product aspects such as brand, size, and color - a task we define as Aspect Affinity. Solving this task improves customer understanding and enables fine-grained personalization in recommendation, search, and marketing. We frame Aspect Affinity as ...
- Scalable Kronecker-Fisher Approximation: Efficient Hessian Analysis for Billion-Parameter Language Models Compression
In this paper, we propose a scalable Kronecker-based approximation that captures cross-layer interactions without storing the entire Fisher matrix, enabling practical Hessian analysis for billion-parameter networks where full computation is infeasible. Our approach reveals consistent vulnerability p...
- Towards One-for-All Robustness Across a Continuum of Threat Levels
Adversarially robust models often overfit to a specific attack budget, necessitating multiple specialized models for diverse and dynamic adversarial environments, a strategy that becomes fundamentally intractable as the threat space grows. This raises an open challenge: can we achieve strong robustn...
- Coverage, Not Targeting: A Structural Regime in Multi-Turn Agent Credit Assignment
Multi-turn agentic RL increasingly treats credit assignment as a targeting problem: given a terminal verifiable reward, per-turn methods localize credit onto the turns that mattered. We identify the structural quantity that predicts when this is the right move, the verifier information density V_d =...
- Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking
Multi-turn jailbreak attacks demonstrate that harmful intent can be distributed across dialogue, yet existing methods obscure what conversational mechanisms drive vulnerability. We introduce BLUEPRINT, a safety-evaluation framework separating a factorized social-influence strategy space from WORLDVI...
- Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts
Sparse mixture-of-experts (MoE) models use an independently parameterized router at each sparse layer to select experts for every token. Prior work has shown that routing decisions across depth can often be predicted from earlier routing signals, suggesting that routing is not fully independent acro...
- Towards a Foundational Ontology for Identifying and Resolving Contradictions in Dialogue-based Human-Robot Interactions
Existing Human-Robot Interaction (HRI) literature has focused on identifying and structuring errors, failures, conflicts, and knowledge issues (called in this work as contradictions) in domain-specific dialogue-based interactions. However, there is still lack of a formal computational framework to r...
- Subcellularly Resolved Single-Cell Embedding Learning with Transcriptomic data, Protein Structure and Localization Information
Existing cell embedding methods predominantly rely on transcriptomic or proteomic measurements and represent each cell as a holistic entity, thereby overlooking the subcellular localization of individual molecules. Moreover, they rarely incorporate protein structural information, despite its fundame...
- AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transformers
World modeling requires a predictive model to maintain and update an internal state adequate for reasoning about the consequences of actions. We introduce the AGI Maze Prediction Datasets and Benchmark, a lightweight controlled testbed for studying this capability in Transformers and other predictiv...
- User Feedback Provides a Unique Signal that LLMs Can not Detect
Harnessing naturally occurring feedback from user interactions offers a promising learning signal for Large Language Models (LLMs). However, recent studies suggest this feedback is inherently noisy and difficult to leverage effectively. We challenge this conception by demonstrating that user feedbac...
- Towards Trustworthy Autonomous Robots: An Explainable AI-Based Decision Framework
Autonomous robots powered by deep learning face a fundamental auditability challenge: when incidents occur, investigators cannot reconstruct why the system made specific decisions. This paper presents TRACE (Transparent Reasoning Architecture for Credible Execution), a decision framework that ensure...