AI News Archive: June 9, 2026 — Part 14
Sourced from 500+ daily AI sources, scored by relevance.
- Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniques
Data assimilation (DA) in subsurface flow entails calibrating model parameters to match observed data, typically at wells, while preserving geological realism. Latent diffusion models (LDMs) provide efficient mappings from high-dimensional geological model space to a low-dimensional latent variable,...
- Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation
Synthetic post-training pipelines commonly filter generated samples with reward models or holistic LLM judges, yet two practices remain rarely examined together: whether the filtering signal is grounded in the source evidence that induced each generation, and whether rejected samples can be systemat...
- TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models. However, rollout-intensive policy optimization is often limited by insufficient reward contrast, arising when overly simple or complex prompts generate...
- Towards Autonomous Accelerator Design: FPGA Accelerator Generation with SECDA
Designing FPGA-based accelerators for modern artificial intelligence workloads requires exploring a large and complex hardware design space that involves architectural parameters, data flow strategies, and memory hierarchies, making the process very time consuming. While existing methodologies such ...
- FADA: Accessible fetal ultrasound interpretation and annotation with a selectively distilled unified vision-language model
A global shortage of trained sonographers limits prenatal ultrasound screening in low- and middle-income countries, where over half of pregnant women receive no skilled sonography. Current deep learning approaches address detection, segmentation, or classification in isolation, each demanding a sepa...
- RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning
Elite humanoid soccer shooting requires whole-body stability, high-impulse whole-body interactions, and accuracy to targets. Motion tracking-driven reinforcement learning (RL) provides stability in whole-body movement coordination, but a fixed reference makes it hard to adapt to varied ball position...
- Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control. While they are known to scale stably in the supervised imitation learning setting, incorporating them into reinforcement...
- Unifying Local Communications and Local Updates for LLM Pretraining
Communication-efficient pre-training of LLMs is increasingly important as training draws on compute distributed across clusters, data centers, and lower-bandwidth links. Many practical methods reduce communication frequency but still rely on synchronous All-Reduce operations that maintain identical ...
- Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models
With the widespread deployment of Multimodal Large Language Models (MLLMs) in social interaction, understanding and controlling their behavior under complex personality conditions is essential. This paper introduces explicit personality conditioning and establishes a systematic evaluation framework ...
- T1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains
Recent advances in reasoning and tool-calling capabilities of large language models (LLMs) have enabled increasingly capable agentic systems. However, existing benchmarks remain limited in task complexity, realism, and domain diversity, and often fail to capture interactions that span multiple domai...
- AgentOS
Manage AI agents, tasks, workspaces from one control layer
- CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs
AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This partially tampers with the untrusted model's trajectory. If the trusted model detects such an intervention, it may infer properties of the monitor and a...
- What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents
Reusing a held-out benchmark adaptively should, in principle, invite overfitting. Yet benchmark-driven machine learning (ML) has produced surprisingly little overfitting in practice. An attractive hypothesis is that successful ML strategies are highly compressible. We study this in the setting of LL...
- AuRA: Internalizing Audio Understanding into LLMs as LoRA
Recent efforts to extend large language models (LLMs) to speech inputs typically rely on cascaded ASR-LLM pipelines, end-to-end speech-language models, or bridge/distillation-based adaptation. While these routes respectively reuse strong pretrained components, enable native speech-language interacti...
- Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving
Learning-based motion planners, despite recent progress, often suffer from temporal inconsistency. Small perturbations across frames can accumulate into unstable trajectories, degrading comfort and safety in closed-loop driving. Several methods attempt to inject history as a static conditioning sign...
- Superficial Beliefs in LLM Decision-Making
We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic underlying decision structure. Using synthetic binary decision settings in which models choose between profiles defined by graded attributes, we comp...
- Structure from Reasoning, Numbers from Search: On-Premise Open LLMs as Structural Priors for Coupled MIMO Controller Tuning
Tuning controllers for strongly coupled multi-input multi-output (MIMO) industrial processes is hard: decentralized classical auto-tuning ignores loop interaction, and local numerical optimization from natural initializations stalls in the resulting non-convex cost landscape. We ask whether on-premi...
- Understanding and mitigating the risks of OpenClaw for non-technical users: A practical guide with Skill
OpenClaw has rapidly emerged as a transformative artificial intelligence (AI) agent framework, and its ability to autonomously execute complex, multi-step tasks has attracted an ever-growing and diverse user base. However, this capability comes with significant risks. While existing research has mad...
- Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning
Large language model unlearning aims to suppress designated undesirable knowledge while preserving benign capabilities. Many unlearning objectives focus on suppressing undesired answers, while recent target-guided variants specify replacement behavior but still leave update locality largely unconstr...
- Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets
Many Markov decision processes (MDPs) in operations research have feasible actions that are state dependent and defined implicitly by various operational constraints. These features make it difficult to use standard deep reinforcement learning (DRL) algorithms, whose action interfaces typically assu...
- Optimizing 2D Input Representations and Sub-phase Fusion Strategies for Differential Diagnosis of Asthma and COPD Using CNN- and GRU-Based Networks
This study aims to explore the performance of the VAR model in comparison with mel-frequency cepstral coefficient (MFCC) matrices and log-mel spectrograms using deep learning. In pulmonary sound classification, spectrogram-based representations suffer from inconsistent temporal dimensions due to var...
- Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning
Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning. However, existing PPO-style trust-region mechanisms remain position-agnostic by enforcing uniform thresholds across all tokens independently. This pointwise treatment conflicts with autoregressive ...
- Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?
The deployment of Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade productivity software is largely untested. We argue that Office automation is an ideal environment for benchmarking document-automation capability, a...
- Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models
Persistent memory systems promise to make LLMs more helpful by storing user beliefs over time. We show they also make models less correct by systematically amplifying sycophancy, wherein models prioritize agreement with users over accuracy. We conduct the first systematic evaluation of this effect, ...
- Generative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature Interactions
As artificial intelligence and machine learning (AI/ML) models become integral to network operations, their lack of transparency poses a significant barrier to operator trust. Existing explainable artificial intelligence (XAI) techniques often fail to bridge this gap for non-specialists, producing t...
- Democratising Camera Trap AI: An Open-Source Model for Detecting UK Mammals
Camera traps have become a cornerstone of biodiversity monitoring, but the artificial intelligence that turns vast quantities of images into usable ecological data is often locked behind commercial platforms or trained on fauna that does not match that of the British Isles. In an attempt to remove b...
- Tizbe
One project memory across every AI tool.
- CLP: Collocation-Length Prediction for Zero-Loss Adaptive Multi-Token Inference
Large language model inference is bottlenecked by autoregressive decoding, where each token requires a full forward pass. Multi-token prediction (MTP) offers a promising acceleration path, but existing approaches suffer from a fundamental architectural flaw: the MTP head for the first token competes...
- Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages
LLM-based coding agents are usually evaluated in familiar software settings: mainstream languages, common libraries, and public repositories. These benchmarks remain important, but they can hide how agents behave when the language itself is unfamiliar. We evaluate six contemporary coding agents on f...
- Recoverable but Not Stationary:Local Linear Structures in Weights and Activations
Task vectors, LoRA, activation steering, and random search around pretrained weights all suggest that learned behaviour can be controlled by linear directions. We ask which linear structures actually exist and on what scale. In a synthetic multitask transformer and LoRA adapters on DistilGPT-2 / GPT...
- A Constrained Natural-Language Interface for Variational Multi-Physics Finite Element Simulations in FEniCS
Large language models can reduce the manual effort required to set up finite element simulations, but they introduce reliability risks when generated solver code lies on the critical path. We present a constrained natural-language interface for multi-physics finite element analysis in which the LLM ...
- Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
Although Large Language Model (LLM) agents have demonstrated strong performance on complex tasks, their learning is often limited by inefficient interaction feedback and static training environments, which hinder broader generalization. To address these limitations, this paper introduces Role-Agent,...
- Pose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject Customization
Subject Customization is a foundational task in modern image generation. By providing a few reference images and a text prompt, users can generate images of a specific object in any desired scene. However, existing methods still struggle to achieve effective pose control for customized subjects. In ...
- Designed by Journalists, but Is It for Readers? Rethinking AI Disclosures and Transparency in News
As newsrooms integrate generative AI, journalists face a disclosure challenge: how to communicate AI involvement in ways that maintain reader trust. Current practice offers two approaches: brief one-line labels or detailed disclosures specifying human oversight, editorial accountability, and error r...
- PhantomBench: Benchmarking the Non-existential Threat of Language Models
Hallucinations, where language models (LMs) generate factually ungrounded responses, pose serious risks, as users tend to blindly rely on them. This is particularly concerning in high-stakes domains, where consequences of such model behavior can lead to significant harms. Despite notable progress in...
- A History-Aware Visually Grounded Critic for Computer Use Agents
Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in complex Graphical User Interface (GUI) environments. However, existing critics suffer from two key limitations: they (1) focu...
- Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields
Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-horizon, high-value professional workflows across diverse domains. C...
- Provenance Tracking in AI Compilers through the Lens of Coalgebra
AI compilers aggressively rewrite computation graphs through normalization, lowering, and optimization, making it difficult to track the provenance of tensors and operators across compilation. Reliable provenance is essential for attaching platform-specific postprocessing, debugging compiler behavio...
- WorldKernel: A World Model is the Coupling Kernel of Admissible Possible Worlds
A common assumption holds that enough observational and interventional data, given to a strong enough predictor, suffices. We report a failure mode that contradicts it. Across hundreds of structural causal models, on identified quantities a strong predictor and a Bayesian baseline both succeed, but ...
- What Do Deepfake Speech Detectors Actually Hear?
Deepfake speech detectors often output a single score without explaining why an audio sample is flagged, where in the signal the evidence lies, or what cues drive the decision. We propose an audio-native explainability pipeline using Integrated Gradients on time-aligned self-supervised representatio...
- Ethical and Technical Limits of Deepfake Speech Datasets
Claims about the robustness and fairness of deepfake speech detectors are only as credible as the datasets used to train and evaluate those systems. We present a dataset-level audit of the deepfake speech landscape. We compile and analyze 39 deepfake speech datasets, examining key attributes includi...
- RAT: Reference-Augmented Training for ASV Anti-Spoofing
We introduce a spoofing countermeasure architecture conditioned on speaker-reference recordings, but observe that it converges to a solution that effectively ignores the reference during inference. Surprisingly, training with a reference channel induces invariance that improves deepfake detection, e...
- Human-AI Teaming Through the Lens of Calibration
We study models for human-AI teaming through the lens of statistical calibration. We assume the team consists of an AI model and human -- both of which are calibrated with respect to some partitioning of the feature space -- and expose how the calibration assumptions propagate into the teaming frame...
- Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
Data tells stories that shape society; the data journalist's job is to turn raw information into stories non-experts can trust. A high-quality news feature takes a newsroom team weeks: hunting for context, running statistics, choosing an angle, and designing visuals. Recent agents handle individual ...
- The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models
This study investigates cross-lingual distributional skew (the Shibboleth Effect) in frontier large language models (LLMs) subjected to sustained adversarial conditions. We develop a multi-agent geopolitical wargame, the Cerulean Sea Crisis, a synthetic maritime territorial dispute designed to mirro...
- Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It
Chain-of-thought (CoT) supervised fine-tuning (SFT) is widely adopted to improve reasoning ability, yet we find that it systematically degrades long-context recall in hybrid linear-attention models. Across architectures including HypeNet and Jet-Nemotron, retrieval performance on Needle-In-A-Haystac...
- Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models
Instruction-tuned LLMs are increasingly converted into reasoning models through post-training to improve multi-step task performance. This conversion is usually optimized for reasoning accuracy, without explicitly preserving the alignment behavior of the instruction-tuned model, such as safe refusal...
- Generative Archetype-Grounded Item Representations for Sequential Recommendation
Sequential recommendation aims to predict users' next interaction with items by analyzing their historical behavior. However, the limited quality of item representations remains a critical bottleneck. While pre-trained large language models (LLMs) can provide rich semantic representations, existing ...
- Measuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder Transfer
Measuring subjective constructs in naturally occurring social media text requires annotation procedures that are theoretically grounded, empirically validated, and transferable to an encoder model for scalable prediction. Using non-English social media posts annotated according to Schwartz's theory ...
- It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO
Warning: This paper contains several toxic and offensive statements. Modern large language models (LLMs) are typically aligned through large-scale post-training to ensure fair and reliable behavior. In this work, we investigate how easily such guardrails can be broken by Group Relative Policy Opti...