Search: “reasoning”

arXiv:2606.08525v1 Announce Type: new Abstract: Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such re

arXiv:2606.08367v1 Announce Type: cross Abstract: Most evaluations of LLM agents look like exams: a discrete task, a clean environment, a score in minutes or hours. We argue that this approach is mism

arXiv:2606.09475v1 Announce Type: new Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior. This supports the `persona selection'

🚨 Fable 5 is something to pay attention to. This is another 'I had early access to the new Mythos-class Anthropic model and I want to tell you what I thought of it' post. I know, I know, it's annoying

arXiv:2507.00322v2 Announce Type: replace-cross Abstract: Despite remarkable advances in coding capabilities, language models (LMs) still struggle with simple syntactic tasks such as generating balanc

arXiv:2606.09079v1 Announce Type: cross Abstract: Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report

arXiv:2606.08945v1 Announce Type: new Abstract: We investigate whether information about time-to-event risk estimated by a Cox proportional hazards model can be transferred into a generative large lan

arXiv:2606.08284v1 Announce Type: new Abstract: Recovering the relative 6-DoF pose between two image groups underlies cross-sequence relocalization and multi-camera rig odometry. Each group carries kn

arXiv:2606.08530v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models achieve strong benchmark performance but still struggle in real-world deployment with unseen objects, background s

arXiv:2606.08194v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) integrate audio perception and language understanding within a unified framework, enabling a wide range of real-wo

arXiv:2606.08440v1 Announce Type: cross Abstract: Robotic grasping is a fundamental capability in robotic manipulation. Yet grasping remains challenging under partial observations. Reliable grasping d

arXiv:2606.08014v1 Announce Type: cross Abstract: Accurate 3D instance segmentation in point cloud data is critical for machine vision applications. Recent advancements leverage multiple pre-trained f

arXiv:2606.08051v1 Announce Type: new Abstract: Financial transaction processing requires extracting structured merchant information from noisy, abbreviated bank transaction strings at scale. Our curr

How do you prove the business value of generative AI to your teams? Technology and finance leaders need to show the clear business value of AI projects to secure ongoing funding. While measuring retur

arXiv:2509.10334v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained device

arXiv:2606.08601v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated impressive potential for time series forecasting. However, existing methods predominantly rely o

arXiv:2606.07865v1 Announce Type: cross Abstract: Scientific machine learning is limited less by model size than by the data it is trained on. Observational data records what happened but not why; tem

Gemma 4 12B is a unified, encoder-free multimodal model designed to bring high-performance intelligence to laptops and released under an Apache 2.0 license. It eliminates separate encoders by projecti

arXiv:2402.13425v3 Announce Type: replace-cross Abstract: It is becoming increasingly common in regression to train neural networks that model the entire distribution even if only the mean is required

arXiv:2606.07819v1 Announce Type: new Abstract: Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications. While post-training quantiz

Gary Marcus critiques an AI response about bullying, arguing that it exemplifies typical large language model output rather than demonstrating genuine artificial general intelligence (AGI). The post s

arXiv:2606.09314v1 Announce Type: new Abstract: Generating high-quality dexterous grasps remains challenging for learning-based methods, which often depend on carefully tuned contact losses or costly

arXiv:2606.08666v1 Announce Type: new Abstract: Robots deployed in human-centric environments routinely receive natural-language descriptions of spatial information ('I left my backpack on the table')

arXiv:2310.10196v3 Announce Type: replace-cross Abstract: Temporal data, including time series and spatio-temporal data, are pervasive in real-world applications. Generated in massive volumes by physi

arXiv:2606.09131v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) commonly inherit the deep, symmetric Transformer backbone designed for unimodal text modeling, and apply the sa

arXiv:2606.08131v1 Announce Type: cross Abstract: Conversational AI is increasingly used for advice, interpretation, reassurance, and decision support in contexts where users may be vulnerable, uncert

A user announced a major update to their Ollama coding assistant featuring Cline, an autonomous coding agent that operates within IDEs and can create, edit files, execute commands, and interact with t

arXiv:2606.09641v1 Announce Type: new Abstract: The dominant paradigm in video retrieval relies on embedding-based full-corpus scanning, which suffers from inherent computational inefficiency and the

arXiv:2606.09483v1 Announce Type: cross Abstract: Long-term memory for an LLM agent is more than retrieving the right passage at the right time. Current memory systems collapse belief revision, causal

arXiv:2511.20397v2 Announce Type: replace Abstract: We present BLINQ, a new model-based algorithm that learns the Whittle indices of an indexable, communicating and unichain Markov Decision Process (M

arXiv:2601.21522v2 Announce Type: replace-cross Abstract: The performance of large language models (LLMs) on verifiable tasks is usually measured by pass@k, the probability of answering a question cor

arXiv:2606.07639v1 Announce Type: cross Abstract: Video understanding is shifting from the offline paradigm -- taking a fully recorded video as input and producing a single answer after it ends -- tow

arXiv:2601.03256v2 Announce Type: replace Abstract: We present Muses, the first training-free method for fantastic 3D creature generation in a feed-forward paradigm. Previous methods, which rely on pa

arXiv:2606.09692v1 Announce Type: cross Abstract: Delegation-scoped execution is not identifiable from standard observables: audit logs and execution traces can be identical under multiple incompatibl

arXiv:2606.08572v1 Announce Type: new Abstract: While Omni-modal Large Language Models (OLLMs) have demonstrated impressive capabilities in jointly processing audio and visual streams, their ability t

arXiv:2602.15829v2 Announce Type: replace Abstract: The superficial alignment hypothesis (SAH) posits that large language models learn most of their knowledge during pre-training, and that post-traini

arXiv:2606.07890v1 Announce Type: new Abstract: Performative prediction studies feedback loops that arise when predictive models are deployed in consequential domains. In these settings, deploying a m

arXiv:2601.19082v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and act on behalf of users. Whether they coo

arXiv:2606.09348v1 Announce Type: new Abstract: Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final

arXiv:2606.08688v1 Announce Type: cross Abstract: Achieving fully automated, physically plausible 3D motion synthesis is a core objective in graphics and generative AI. However, configuring complex en

arXiv:2606.08563v1 Announce Type: new Abstract: While global data-driven models excel at predicting continuous atmospheric variables, three-dimensional hydrometeor forecasting remains challenging due

arXiv:2606.07527v1 Announce Type: cross Abstract: The prevailing paradigm for training LLMs has evolved to rely on a massive post-training phase consisting of SFT and RL. In this position paper, we ar

arXiv:2606.09396v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation and often serves as the initialization stage for reinforcement le

arXiv:2606.08500v1 Announce Type: cross Abstract: Software engineering agents (SWE agents) increasingly work through tool-mediated trajectories in real repositories, yet their behavior remains difficu

arXiv:2606.09711v1 Announce Type: new Abstract: Reward hacking is usually studied after it becomes visible, once a model earns high proxy reward while failing the intended task. We instead study what

arXiv:2606.08212v1 Announce Type: new Abstract: Solving machine learning problems is complex and typically reserved for experts. Over the past two decades, systems have emerged to support non-experts.