Knowledge catalogue
arXiv:2609.12437v1 Announce Type: new Abstract: Adaptive RAG often uses retrieval-time signals to decide whether another retrieval, reranking, or multimodal step should run. We ask whether these signa
arXiv:2510.26046v3 Announce Type: replace-cross Abstract: Class imbalance complicates probabilistic classification because standard training objectives emphasize majority-class performance. Synthetic
arXiv:2602.13177v2 Announce Type: replace-cross Abstract: The performance of online mirror descent depends critically on the geometry induced by its mirror map, yet standard algorithms largely rely on
arXiv:2604.05793v2 Announce Type: replace-cross Abstract: In LLM agent pipelines, prompt privacy risk propagates beyond a single model call: raw user content enters retrieval queries, memory writes, t
arXiv:2609.12303v1 Announce Type: new Abstract: Small models are made more capable through distillation from a larger one that shares their tokenization scheme. However, do distilled byte and token mo
arXiv:2609.12641v1 Announce Type: new Abstract: Robot foundation models achieve strong in-distribution performance but often degrade under visual distribution shifts. When learning to generate actions
arXiv:2609.12218v1 Announce Type: cross Abstract: The growing use of electroencephalography (EEG) motivates automated analysis that is accurate, transferable, and deployable on constrained hardware. R
arXiv:2609.12454v1 Announce Type: new Abstract: Vision-Language Models such as CLIP enable effective few-shot medical anomaly detection (AD) via strong image-text semantic alignment. However, their gl
arXiv:2609.12575v1 Announce Type: new Abstract: Ambiguity is often treated as a bug for AI systems to resolve---but in human communication and culture, ambiguity can also be a generative resource. Fro
arXiv:2609.12162v1 Announce Type: cross Abstract: Draft-verify-revise is a common LLM orchestration pattern for scaling inference-time compute. One LLM drafts, a second critiques the draft and provide
arXiv:2504.07133v2 Announce Type: replace-cross Abstract: We revisit the problem of estimating k linear regressors with self-selection bias in d dimensions with the maximum selection criterion, as int
arXiv:2609.12002v1 Announce Type: new Abstract: LLMs are increasingly used as automated judges for model training and evaluation, yet individual judges exhibit systematic biases that undermine reliabi
arXiv:2609.13060v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) offer promising parallel generation capabilities but lag behind autoregressive models in complex reasoning and tool-use
arXiv:2606.23189v2 Announce Type: replace-cross Abstract: Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-appli
arXiv:2609.12365v1 Announce Type: new Abstract: In the VTaC benchmark 71% of ventricular-tachycardia alarms are false, but silencing a real one can delay recognition of a dangerous arrhythmia. We refr
arXiv:2609.12014v1 Announce Type: new Abstract: Safe offline reinforcement learning assumes a cost function on every transition. We ask what remains possible when safety can be judged only by comparin
arXiv:2609.12163v1 Announce Type: new Abstract: Existing evaluations of concept unlearning in text-to-image (T2I) diffusion models primarily rely on attack success rates obtained through automated adv
arXiv:2609.12221v1 Announce Type: new Abstract: Maintaining consistency over long spatial and temporal horizons remains a fundamental challenge in large-scale LiDAR SLAM, particularly when integrating
arXiv:2609.12509v1 Announce Type: new Abstract: Evaluation of vision-language models (VLMs) for multimodal mathematical reasoning remains limited for low-resource languages and for geometry problems t
arXiv:2609.12243v1 Announce Type: new Abstract: Inference-time power sampling via Sequential Monte Carlo (SMC) can substantially improve large language model (LLM) reasoning without requiring post-tra
arXiv:2511.20941v2 Announce Type: replace-cross Abstract: Two-sample tests have been extensively employed in various scientific fields and machine learning to discriminate whether two sets of samples
arXiv:2609.12584v1 Announce Type: new Abstract: Instruction-tuning datasets for large language models (LLMs) are often large, redundant, and imbalanced, limiting efficient adaptation. Naive large-batc
arXiv:2609.12791v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has empowered Large Language Models (LLMs) to tackle knowledge-intensive tasks. However, navigating global, heterog
arXiv:2609.13011v1 Announce Type: new Abstract: Data-driven driving simulators command accelerations and steering rates from a fixed grid without constraining the realized accelerations and jerks. As
arXiv:2609.12502v1 Announce Type: new Abstract: Exploring unknown environments with multi-robot teams can improve efficiency by allowing robots to explore in parallel. However, realizing these gains r
arXiv:2609.12489v1 Announce Type: cross Abstract: Test case synthesis is crucial for evaluating and ranking programs generated by large language models (LLMs). However, constructing high-quality test
arXiv:2609.12374v1 Announce Type: new Abstract: Dashboard-mounted gaze trackers often lose sight of the driver's eyes during large head rotations, including shoulder checks, mirror glances, and inters
arXiv:2609.13117v1 Announce Type: new Abstract: Full-duplex evaluation often emphasizes whether an agent keeps speaking or stops. That binary cannot express a third response humans use routinely: cont
arXiv:2609.12737v1 Announce Type: new Abstract: Robots are increasingly used in unstructured environments. The need for them to safely grasp unknown objects without damaging them becomes crucial. Huma
arXiv:2609.12785v1 Announce Type: new Abstract: Classical convergence guarantees for stochastic gradient methods typically assume Lipschitz-smooth objectives and finite-variance gradient noise, both f
arXiv:2609.12826v1 Announce Type: new Abstract: In order to design conservation and restoration strategies to counter the global decline of coral reefs, ecological monitoring of reefs needs to be scal
arXiv:2609.12620v1 Announce Type: new Abstract: The increasing adoption of machine learning in network and distributed security systems has created an urgent need for mechanisms that can selectively a
arXiv:2609.11970v1 Announce Type: cross Abstract: Qualitative research is widely used in the human and social sciences, characterized by a deep understanding of phenomena through the interpretation of
arXiv:2609.12086v1 Announce Type: cross Abstract: Assistants built on large language models are expected to write as their user would, and the dominant approach is single-channel: preferences summaris
arXiv:2609.12244v1 Announce Type: new Abstract: In sub-terahertz (sub-THz) communications, the coupling of ultra-wide bandwidth and severe phase noise (PN) impairments renders conventional joint chann
arXiv:2609.12354v1 Announce Type: new Abstract: Long-term conversational agents must answer user queries by recalling information from extended dialogue histories, yet directly using the full history
arXiv:2609.12758v1 Announce Type: new Abstract: Recovering unmanned aerial vehicles (UAVs) in maritime environments is challenging due to wind turbulence and ship-deck motion, making it a valuable tes
arXiv:2609.12316v1 Announce Type: new Abstract: Collecting high-quality robot data remains a fundamental challenge for training robot foundation models. Task and motion planning (TAMP) offers a scalab
arXiv:2609.11997v1 Announce Type: new Abstract: Learning robust representations for time-series signals under noise and distribution shifts remains challenging, especially in clinical applications suc
arXiv:2604.08335v2 Announce Type: replace Abstract: We present a feedforward graph architecture in which heterogeneous frozen large language models serve as computational nodes, communicating through
arXiv:2609.12400v1 Announce Type: cross Abstract: This paper presents a novel approach to hexapod locomotion by evolving each leg's gait independently through a decentralized evolutionary algorithm. U
arXiv:2609.11958v1 Announce Type: new Abstract: Olfaction played an indispensable role throughout human evolution and civilization. Even in the contemporary era of advanced technology, olfaction remai
arXiv:2603.27510v2 Announce Type: replace Abstract: Statistical fairness metrics in AI-driven credit decisions conflate two causally distinct mechanisms: discrimination operating directly from a prote
arXiv:2512.23829v3 Announce Type: replace-cross Abstract: Inverse problems are important mathematical problems that seek to recover model parameters from noisy data. Since inverse problems are often i
arXiv:2609.12929v1 Announce Type: new Abstract: Dementia affects an estimated 57 million people worldwide, and for most families the hardest part of care is not memory loss but the behavioral and psyc
arXiv:2603.12064v3 Announce Type: replace Abstract: We address the challenging problem of dense dynamic scene reconstruction and camera pose estimation from multiple freely moving cameras -- a setting
arXiv:2609.12411v1 Announce Type: new Abstract: Prohibited-item detection in X-ray imagery remains challenging due to object superposition, weak texture, and material clutter which obscure both semant
arXiv:2511.23372v2 Announce Type: replace Abstract: The increasing industrial demand for alternative actuators over conventional electromagnetism-based systems having limited efficiency, bulky size, c
arXiv:2609.12678v1 Announce Type: new Abstract: Short-video platforms have become a primary news source for the public, which has also enabled the widespread dissemination of fake news videos. We stud
arXiv:2609.12245v1 Announce Type: new Abstract: Diffusion-based robot policies have become widely used in robotic manipulation, where they are typically trained with behavior cloning. However, policie
arXiv:2609.13047v1 Announce Type: cross Abstract: Humans organize knowledge into a taxonomy of concepts with nested levels of abstraction and a basic level at which people recognize and name objects w
arXiv:2609.12994v1 Announce Type: new Abstract: Heavy-tailed empirical spectral densities of neural-network weight matrices are widely used as diagnostics of implicit self-regularization, but the step
arXiv:2609.12157v1 Announce Type: cross Abstract: We present a framework for tracking topological features directly within continuous implicit models. Such models, including implicit neural representa
arXiv:2609.12923v1 Announce Type: cross Abstract: A single SM utilization percentage can make an LLM inference workload look compute-saturated while hiding how much useful work is being done. The prob
arXiv:2609.12651v1 Announce Type: new Abstract: While Reinforcement Learning from Human Feedback (RLHF) is the standard paradigm for aligning large language models with human preferences, its effectiv
arXiv:2609.12959v1 Announce Type: new Abstract: While offering significant promise for diverse applications, pattern-oriented swarms encounter multifaceted challenges in geometric control, self-organi
arXiv:2609.12444v1 Announce Type: cross Abstract: Simulated societies of large language model agents are used to study online polarization, and separately to study collective intelligence, but the two
arXiv:2609.12446v1 Announce Type: cross Abstract: Social-deduction games such as Werewolf are increasingly used to evaluate LLM agents, but existing evaluations often rely on final game outcomes. We p
arXiv:2609.12674v1 Announce Type: new Abstract: Advanced large language models (LLMs) with long context windows can substantially reduce input truncation in document-level machine translation (DocMT).
arXiv:2609.12090v1 Announce Type: new Abstract: Video models increasingly use memory to preserve information over long sequences, with the assumption that gains come from retrieving and using the corr