Developer Tools B

Arch Linux now believes a malware incident affecting more than 1,500 packages is under control, an episode that highlights ongoing supply-chain security risks in software package ecosystems.

Simon Willison comments on the US government's national-security export-control directive suspending all foreign-national access to Fable 5 and Mythos 5, calling the move extraordinary and questioning its rationale and impact.

Simon Willison updated his browser tool for OpenAI's WebRTC realtime audio API. It now supports the newer realtime voice model touting GPT-5-class reasoning, and lets users paste document text as context for spoken conversations about it.

Microsoft Research reports its autonomous malware-analysis agent Project Ire reverse-engineered a new specimen and identified LOTUSLITE traits that most major EDR tools failed to detect, underscoring AI's expanding role in threat analysis.

The paper identifies a small set of attention heads, dubbed gaze heads, that track the image region a vision-language model is currently describing. Intervening on the top ~100 of them can steer the model to describe any chosen region.

Persona-Pruner is a pruning approach that sculpts lightweight language models specialized for role-playing. It aims to retain consistent, persona-driven interaction while reducing model size.

The paper studies active learning for multi-group mean estimation framed as a d-armed bandit minimizing max-risk. It introduces a complexity measure characterizing the difficulty of adaptive budget allocation.

Cotton underpins the textile industry, so accurate detection of cotton leaf disease is crucial for economic stability. The paper proposes CottonLeafVision, an explainable and robust deep learning framework for classifying cotton leaf diseases.

HumP-KD is a hybrid, uncertainty-aware multi-stage progressive knowledge distillation framework for fire classification. It targets models that are simultaneously accurate and efficient for real-time use.

The work casts online inventory optimization as online convex optimization with memory, where carryover makes the feasible set history-dependent. It develops an optimal hidden-target learning method on general convex sets.

AgentSpec studies scaffolded LLM agents that combine reasoning, memory, reflection, and action through controlled composition. It aims to isolate how each component contributes to overall performance.

As AI automates real-world computer vision applications such as autonomous vehicle control, this paper demonstrates acoustic adversarial attacks that can disrupt CV systems, highlighting a new physical, sound-based attack surface.

Time-stamped interaction logs objectively record digital app usage, but their granularity and noise obscure meaningful insights into work. The paper proposes abstracting cross-domain action sequences into interpretable workflows.

The paper addresses combinatorial semi-bandit identification of optimal structures under nonlinear reward associations. It leverages separable signals to reduce sampling and computational cost.

The work studies which uncertainty directions a model must cover in affine robust optimization defined by a finite dictionary and budget. It proposes a sparse design selecting the directions that matter.

Transformer-based ASR models like Whisper are accurate but hard to interpret, and existing XAI methods lack faithfulness and temporal precision. The paper proposes an entropy-guided explainability approach for such audio models.

Verifier-driven self-DPO, where a frozen verifier scores candidates to form preference pairs, is a common recipe for self-improving vision-language models. The paper shows that under this setup VLMs can regress on new tasks when the verifier misbehaves.

The paper assesses how well AI generates culturally localized stories. It characterizes the ways cultural localization appears in generated narratives.

Diffusion language models are marketed as parallel decoders, yet their real token-commit order is rarely measured. Instrumenting DiffusionGemma, the paper shows it is neither purely parallel nor sequential.

Through computational analysis, this paper argues that the three movements of Beethoven's Moonlight Sonata (Op. 27 No. 2) instantiate three distinct machine learning architectures by structural correspondence rather than mere analogy.

Survival prediction is central for healthcare providers and clinical researchers. The paper introduces expert-driven survival machines that improve risk stratification and interpretability across multiple clinical cohorts.

Wearables and smartphones generate rich behavioural time series for proactive health interventions, yet systematic comparisons of forecasting architectures are lacking. The paper benchmarks deep learning architectures for multi-horizon behavioural forecasting in mobile health.

Online group chats have rarely-stated local conversational norms. LoSoNA is a benchmark measuring whether LLM-based agents can recognize and adapt to these local social norms.

Large audio-language models perform well on audio understanding yet still struggle with reasoning. The paper introduces AudioDER, a deduplication-enhanced reasoning dataset for post-training large audio-language models.

LLM agents increasingly run as long-lived autonomous runtimes that schedule jobs, call tools, maintain memory, and push results to humans. This longitudinal study of one persistent system presents a taxonomy of its silent failures.

Identifying persuasive rhetorical cues matters for detecting manipulation, AI safety, and health communication. The paper proposes Persuasion Index, a theory-guided framework for persuasion analysis.

A core role of personal-agent memory is turning stored information and prior interactions into future-oriented assistance. StreamMemBench provides a streaming evaluation of agent memory using cues from what the agent observes and how users interact.

Emulators cheaply reproduce regional climate models' downscaling, linking global-model predictors to high-resolution fields. The paper assesses the added value of diffusion-based generative machine learning for regional climate model emulation.

CANNs offer interpretable material model discovery but have relied on stress-supervised data. CANN-EUCLID enables unsupervised constitutive model discovery directly from full-field measurement data.

Two-finger grippers dominate manipulation research but are limited by their form factor. ORCA is an open-source platform to support research on more dexterous robotic manipulation.