3,698 items tracked: 33 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2607.02368v4 Announce Type: replace-cross Abstract: Researchers are increasingly prompting language models with cultural personas so that they answer questionnaires as diverse human groups would.
arXiv:2607.02520v2 Announce Type: replace-cross Abstract: Automated research agents increasingly generate code, retrieve literature, and draft scientific artifacts, but they often fail to verify whether generated experim…
arXiv:2607.05458v2 Announce Type: replace-cross Abstract: The execution harness is a critical component of LLM agents, shaping how the agent interacts with its environment and organizes multi-step execution.
arXiv:2607.07368v2 Announce Type: replace-cross Abstract: AI control is a family of techniques to prevent an AI with malicious goals from subverting its operator's intent.
arXiv:2607.08436v2 Announce Type: replace-cross Abstract: Egocentric human data offers scalable supervision for robot manipulation.
arXiv:2607.09988v4 Announce Type: replace-cross Abstract: Recommendation systems, from traditional multi-stage to recent unified generative architectures, face challenges in incorporating diverse contextual signals, such…
arXiv:2607.11889v3 Announce Type: replace-cross Abstract: Large language models trained on unrestricted internet corpora inevitably embed information from the future, introducing lookahead bias that compromises the valid…
arXiv:2607.19020v5 Announce Type: replace-cross Abstract: Clinical prediction models in intensive care degrade as data shift, and regulators such as the FDA ask developers to specify bounded update protocols in advance.
arXiv:2607.19430v3 Announce Type: replace-cross Abstract: AI assistants increasingly work as teams, where one model makes a plan, others search the web, use tools, or read stored information, and another writes the final…
arXiv:2607.22165v2 Announce Type: replace-cross Abstract: LLM-based database agents show promise, but differences in task scope, testbeds, and success criteria hinder direct comparison.
arXiv:2607.23976v2 Announce Type: replace-cross Abstract: Whether a language model agrees with a user depends on how the user asks.
arXiv:2607.26455v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquired knowled…
arXiv:2607.27384v2 Announce Type: replace-cross Abstract: Clinical language models are evaluated on vignettes written in a clinician's voice, but patients describe the same illness in their own.
arXiv:2607.27964v3 Announce Type: replace-cross Abstract: Ensuring behavioural correctness in communication protocols is a central challenge in distributed software systems, as subtle inconsistencies can lead to deadlock…
arXiv:2607.28022v2 Announce Type: replace-cross Abstract: Large language model training in open-ended domains lacks verifiable rewards, making task preferences difficult to formalize as effective supervision.
arXiv:2607.28649v2 Announce Type: replace-cross Abstract: COSI-Lab presents a multimodal multi-sensor dataset of a real interdisciplinary scientific workshop with 32 academics at an international conference.
arXiv:2607.28916v2 Announce Type: replace-cross Abstract: Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental challenge.
arXiv:2608.26019v2 Announce Type: replace-cross Abstract: On-policy self-distillation (OPSD) combines student generated trajectories with dense supervision from a privileged teacher of the same model.
arXiv:2609.00982v2 Announce Type: replace-cross Abstract: Playing the user with a large language model is standard in scalable evaluation, and has a repeatedly diagnosed failure: the simulated user is excessively coopera…
arXiv:2609.01281v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) policies generate executable robot actions, but plausible proposals can have different consequences for the task.
arXiv:2609.05540v2 Announce Type: replace-cross Abstract: Many medical conditions require clinical assessment of symptoms, history, and functioning rather than judgments from appearance.
arXiv:2610.14005v1 Announce Type: new Abstract: Under the accelerated pace of AI development, any benchmark whose difficulty is calibrated with humans or current AI systems becomes circular, or saturates soon.
arXiv:2610.14149v1 Announce Type: new Abstract: VETNET represents an ecosystem of live benchmark datasets and evaluation frameworks designed to accelerate AI-driven innovation in animal science and veterinary medicine th…
arXiv:2610.14180v1 Announce Type: new Abstract: Organisations that want language-model agents for security work face a choice between open-weight models, which they can run and audit themselves, and far more expensive cl…
arXiv:2610.14277v1 Announce Type: new Abstract: Tensor parallelism ends every layer with an all-reduce that sits between two dependent matrix multiplications, so its cost cannot be hidden and grows as compute outpaces in…
arXiv:2610.14294v1 Announce Type: new Abstract: Conditional diffusion models can generate high-quality images that align closely with a given prompt.
arXiv:2610.14334v1 Announce Type: new Abstract: In Model Context Protocol (MCP) systems, LLMs select tools from metadata rather than from their implementations.
arXiv:2610.14356v1 Announce Type: new Abstract: AI-enabled systems must remain dependable when the conditions under which they operate change (e.g., due to input perturbations, distribution shifts, or changes in external…
arXiv:2610.14360v1 Announce Type: new Abstract: Large language model (LLM) alignment often assumes that the user interacting with a model is also the primary beneficiary of its behavior.
arXiv:2610.14389v1 Announce Type: new Abstract: Benchmark scores tell us what an LLM can do, but not how much energy is required to deliver that capability.
arXiv:2610.14487v1 Announce Type: new Abstract: Generative recommendation models based on autoregressive decoding have been adopted as alternatives to classical ranking-based systems.
arXiv:2610.14489v1 Announce Type: new Abstract: Reusable wearable PPG representations should capture local pulse morphology and broader physiological regularities.
arXiv:2610.14495v1 Announce Type: new Abstract: Explainer videos -- a worked geometry problem, why the sky is blue, how a dynasty fell -- are usually one more target for pixel video generation.
arXiv:2610.14507v1 Announce Type: new Abstract: Generative modeling offers a promising solution to the scarcity of labeled clinical electroencephalography (EEG) data under strict privacy constraints.
arXiv:2610.14523v1 Announce Type: new Abstract: ScienceBuddy-PV adapts the ScienceBuddy recursive-in-recursive design to panvascular intervention research through a structured evidence ledger, device-vessel ontology, abs…
arXiv:2610.14525v1 Announce Type: new Abstract: Test-Time Discovery (TTD) aims to recognize known classes and detect novel ones while the model is already deployed, operating directly on a continual unlabeled test-time s…
arXiv:2610.14539v1 Announce Type: new Abstract: Real-world business requests often leave key requirements unstated because frontline practitioners struggle to articulate rules they know from experience.
arXiv:2610.14542v1 Announce Type: new Abstract: Multimodal benchmarks are central to evaluating whether models can reason over information from multiple modalities.
arXiv:2610.14570v1 Announce Type: new Abstract: Large language models (LLMs) support social simulation, but faithfully reproducing real users requires grounding both structured platform decisions and language in sparse,…
arXiv:2610.14573v1 Announce Type: new Abstract: Execution is often used as terminal feedback: it scores a generated program, but the resulting state is not used for another learning action.
arXiv:2610.14576v1 Announce Type: new Abstract: As frontier LLMs gain more capabilities, the cost to run them also goes up.
arXiv:2610.14605v1 Announce Type: new Abstract: Current evaluations of multimodal unlearning typically focus on whether a model stops outputting target information.
arXiv:2610.14625v1 Announce Type: new Abstract: Recursive self-improvement (RSI) offers a route to AI systems that participate in their own continued development.
arXiv:2610.14643v1 Announce Type: new Abstract: Clinical speech reveals identity through both spoken identifiers and voice, yet its pauses, delivery, and speaker roles can also carry useful clinical evidence.
arXiv:2610.14644v1 Announce Type: new Abstract: Fine-grained mixture-of-experts (MoE) models commonly increase expert count by narrowing each expert, treating expert shape as a by-product of routing granularity.
arXiv:2610.14659v1 Announce Type: new Abstract: Streaming speech assistants can launch tools before users finish speaking, overlapping execution with incoming speech to reduce user waiting time.
arXiv:2610.14680v1 Announce Type: new Abstract: Sign Language Recognition (SLR) presents complex challenges due to variable signing speeds and spatial intricacies.
arXiv:2610.14693v1 Announce Type: new Abstract: Explicit point correspondence is attractive for adapting video generators: it describes how visible surfaces move, but can overwrite the appearance prior learned by a large…
arXiv:2610.14699v1 Announce Type: new Abstract: The design of high-affinity, target-specific protein binders is central to the development of modern therapeutics.
arXiv:2610.14707v1 Announce Type: new Abstract: Expert-aligned "taste" benchmarks should reward craft judgment, not the ability to game the test.