Stories tagged science & research.
arXiv
arXiv:2609.25143v1 Announce Type: cross Abstract: Unsupervised Continual chunking is a fundamental problem in machine learning and neuroscience, where the goal is to identify groups of states that frequently co-occur in temporal sequences. A key challenge is to form accurate chunks while…
arXiv
arXiv:2609.25755v1 Announce Type: cross Abstract: Applying large language models to Traditional Chinese Medicine (TCM) prescription generation reveals three clinically critical gaps: models produce end-to-end mappings without auditable reasoning following the li-fa-fang-yao paradigm (SR Gap), treat…
arXiv
arXiv:2609.25108v1 Announce Type: cross Abstract: Visual data is increasingly consumed by machine-vision systems rather than by human observers. Image Coding for Machines (ICM) compresses images assuming the main observer is a computer vision application and that the human observer needs to inspect…
arXiv
arXiv:2609.25048v1 Announce Type: cross Abstract: How many prompts does on-policy distillation (OPD) need, and how does the answer depend on the student policies that generate its training responses? We study these two controls jointly: prompt breadth and rollout refresh. A 3x3…
arXiv
arXiv:2609.25674v1 Announce Type: cross Abstract: Lower cost open source robots and reinforcement learning (RL) simulation tools create new opportunities for precollege students to engage with contemporary robotics. However, translating a complete research workflow, spanning mechanical assembly…
arXiv
arXiv:2609.26779v1 Announce Type: new Abstract: Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context windows. We develop CliffCompaction, an autocompaction technique that reduces cost by up to 50%…
arXiv
arXiv:2609.25760v1 Announce Type: new Abstract: Using large language models (LLMs) to simulate diverse human populations has the potential to transform many aspects of computational social science, yet many evaluations score the average response rather than the spread of opinion within real groups…
arXiv
arXiv:2609.25586v1 Announce Type: cross Abstract: Large language models increasingly support decisions where values are in tension, yet little is known about whether interacting with them changes which values users prioritize. In a preregistered study, 200 U.S. adults interacted with ChatGPT…
arXiv
arXiv:2609.25678v1 Announce Type: new Abstract: Large language model (LLM) agents must generalize from tools seen during training to unseen tools at deployment. A key challenge is tool trialing, i.e., excessive trials waste the interaction budget, whereas selective trials enable exploration of…
arXiv
arXiv:2609.25618v1 Announce Type: new Abstract: Reinforcement learning (RL)-based post-training has become an effective approach for eliciting reasoning capabilities in large language models (LLMs). However, adapting post-RL models to new knowledge domains or behaviors through subsequent supervised…
arXiv
arXiv:2609.25376v1 Announce Type: cross Abstract: Post-training quantization reduces the memory requirements of vision-language-action (VLA) models, but precision selection must account for the interaction between layer scope, numerical format, and calibration. We introduce \textbf{VLAQuantBench}…
arXiv
arXiv:2609.25575v1 Announce Type: new Abstract: Fine-tuned Large Language Models (LLMs) significantly advance Automated Theorem Proving (ATP), but are often deployed as guiding policies within tree search rather than for single-attempt generation. Recent work shows cross entropy is suboptimal for…
arXiv
arXiv:2609.25496v1 Announce Type: new Abstract: In this paper, we motivate the need for a participatory speech dataset creation framework through a case study of the LGBTQIA+, or queer, community - a community with documented concerns about AI and reported harms, including attempts to develop…
arXiv
arXiv:2609.25189v1 Announce Type: cross Abstract: Generative search systems rank products and services for consequential decisions, and publishers can cheaply make candidate text look relevant. Yet evidence status is not a text property but a claim-evidence relation: text-only rankers and defenses…
arXiv
arXiv:2609.25466v1 Announce Type: new Abstract: Hand gesture recognition is a key component in human-computer interaction (HCI), enabling intuitive interfaces for applications in gaming, virtual reality (VR), robotics, and more. This study integrates transformer-based machine-learning models for…
arXiv
arXiv:2609.25036v1 Announce Type: new Abstract: Dynamic Gaussian Splatting provides an explicit representation of evolving 3D scenes, but existing approaches are primarily optimized for reconstruction, future-state generation, or rendering rather than for learning reusable predictive dynamics. We…
arXiv
arXiv:2609.25154v1 Announce Type: cross Abstract: AI-generated imagery evolves faster than benchmark-specific detector evaluations, making a single score an incomplete account of generalization. This paper evaluates Neural Defend ARCAS 1B across benchmark families without benchmark-specific…
arXiv
arXiv:2609.25050v1 Announce Type: cross Abstract: We introduce FrontierMath Erd\H{o}s (FME), a benchmark of 68 Erd\H{o}s problems that are open as of August 2026. To solve a task in FME, AI systems must resolve (prove or disprove) one of the 68 conjectures in the proof assistant Lean. Our 68…
arXiv
arXiv:2609.15322v3 Announce Type: replace-cross Abstract: Pretrained driving vision-language models (VLMs) integrate visual, route, language, and driving context into rich driving priors, yet their representation objectives remain separated from continuous driving planning. Existing methods…
arXiv
arXiv:2608.03079v2 Announce Type: replace-cross Abstract: Breast core needle biopsy (CNB) is central to breast cancer diagnosis yet remains challenging because limited tissue sampling, lesion heterogeneity, and subtle morphologic overlap can obscure subtype distinctions. We developed CorePath, a…
arXiv
arXiv:2609.25134v1 Announce Type: cross Abstract: This paper presents a probabilistic perspective on large language models (LLMs), developed with the aim of bringing together, in a single self-contained account, tools that are usually treated separately across the literature. LLMs are described…
arXiv
arXiv:2607.14109v2 Announce Type: replace-cross Abstract: Probing the capabilities of Large Language Models (LLMs) and building robust solutions for Multiple-Choice Question Answering (MCQA) remain central challenges in natural language understanding. Furthermore, the rapid proliferation of LLMs…
arXiv
arXiv:2609.25082v1 Announce Type: cross Abstract: Quantum machine learning (QML) is increasingly recognized as one of the most promising near-term applications of quantum computing, viewed as a next-frontier candidate beyond purely classical approaches. Hybrid quantum-classical models…
arXiv
arXiv:2606.14629v2 Announce Type: replace-cross Abstract: Verifier reliability is not portable across tasks. A verifier-guided self-DPO pipeline with genuine held-out gains on MathVista (+9.6 points on self-training data, +8.0 held out) can be harmful on MMMU. The failure is invisible from the…
arXiv
arXiv:2606.24369v3 Announce Type: replace Abstract: Reinforcement learning (RL) has become a dominant post-training paradigm, driving the emergence of high-performance RL systems such as veRL for autoregressive large language models (LLMs). In parallel, diffusion-oriented RL algorithms, e.g…
arXiv
arXiv:2609.26758v1 Announce Type: new Abstract: Typed decision models are built for settings where model outputs are consumed directly by software. Instead of generating free-form text, they return a decision over a predefined set of options. By construction, every output conforms to the required…
arXiv
arXiv:2605.12061v2 Announce Type: replace Abstract: Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits their ability to recover complete evidence chains from partial cues…
arXiv
arXiv:2508.07292v4 Announce Type: replace Abstract: Endoscopic diagnosis is an iterative process in which clinicians acquire, compare, and verify local visual evidence before reaching a conclusion. Current AI systems do not adequately support this process because fine-grained evidence acquisition…
arXiv
arXiv:2609.26532v1 Announce Type: new Abstract: LLM agents often use generative models for bounded decisions, raising the question of when these decisions can be handled more efficiently without reducing task success. We study REFLEX, an agent architecture that uses Jev as a fast, typed decision…
arXiv
arXiv:2609.26780v2 Announce Type: cross Abstract: Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each statement concerns, how individuals perceive one another, what…