arXiv:2610.29618v1 Announce Type: cross Abstract: Object detection models for autonomous driving commonly experience substantial performance drops when…
Block Diffusion for Longitudinal EHR: Accuracy, Efficiency, and Representation Trade-offs
arXiv:2610.29533v1 Announce Type: cross Abstract: Autoregressive (AR) models have proved effective for zero-shot prediction from longitudinal electronic…
Keeping Time vs. Understanding Time: Neither Alone Explains Temporal Reasoning in LLMs
arXiv:2610.29507v1 Announce Type: cross Abstract: Temporal reasoning is widely assumed to decompose into two modes: temporal arithmetic (date and time…
Are Joint-Embedding Predictive Objectives Effective for Longitudinal EHRs?
arXiv:2610.29528v1 Announce Type: cross Abstract: Masked language modelling (MLM) is the dominant pretraining objective for transformer encoders applied…
Mitigating Query Shortcuts in Chain-of-Thought with Context-Aware Decoding
arXiv:2610.29518v1 Announce Type: cross Abstract: While Chain-of-Thought (CoT) prompting improves the reasoning performance of large language models…
Kyutai CADRE: Video Autoencoders That Cut World Model Lag Below 230 ms
Kyutai released CADRE, a family of 7 open causal diffusion video autoencoders for interactive world models. World models built on CADRE run at 20 fps on 1…
Stochastic Pruning of the DPO Computation Graph: 1.4x Faster Training and Lower Peak Memory
arXiv:2610.29538v1 Announce Type: cross Abstract: Direct preference optimization (DPO) incurs training costs in output scoring, sequence execution, and…
Rethinking Agentic Model Orchestration for Time Series Forecasting
arXiv:2610.29504v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) perform unevenly across forecasting tasks. Recent work uses…
Harness Scaling for Generalizable Agentic Reinforcement Learning
arXiv:2610.29458v1 Announce Type: cross Abstract: Agent harnesses have become a central component of modern agentic systems, shaping how models use tools,…
A Strong MoE Is All You Need for Process Supervision
arXiv:2610.29498v1 Announce Type: cross Abstract: Process reward models (PRMs) provide fine-grained supervision for multi-step reasoning, yet obtaining…
OmniSimulator: Aligning Small Language Models for Authentic Heterogeneous Behavior Modeling
arXiv:2610.29472v1 Announce Type: cross Abstract: Large language models (LLMs) have shown great potential as general-purpose user simulators for…
Moonshot AI launches new flagship Kim K3.1 Pro model with 3T parameters
Moonshot AI today introduced Kim K3.1 Pro, a large language model that can perform some tasks better than Claude Opus 5.5 and GPT-6 Astra. The LLM is a…
Generative Modeling via Nonlinear Schr\”odinger Bridges and Branching Diffusions
arXiv:2610.29476v1 Announce Type: cross Abstract: We propose a new generative modeling framework grounded in forward-backward partial differential…
LLMSeg: Training-Free Text-Prompted Image Segmentation with B-Splines
arXiv:2610.29409v1 Announce Type: cross Abstract: Promptable segmentation models such as SAM 3 achieve remarkable open-vocabulary performance but require…
Reading the Mask: Descriptor-Grounded BI-RADS Rationale Generation for Breast MRI Segmentation
arXiv:2610.29358v1 Announce Type: cross Abstract: Deep learning based models accurately delineate tumours on dynamic contrast-enhanced MRI (DCE-MRI), but…
Beyond Small Talk: Modeling Disclosure Trajectories in Human-AI Conversation
arXiv:2610.29413v1 Announce Type: cross Abstract: Recently, we see a rise in conversational agents as a form of social and emotional support, where…
Dayforce to Acquire Ribbon AI to Bring Conversational Interviews Into Agentic Recruiting
For employers filling hundreds of frontline positions, the first interview can become the slowest part of the hiring process. Dayforce is moving to…
Parallelizable Probabilistic Latent Reasoning for Diverse Reasoning Trajectories
arXiv:2610.29385v2 Announce Type: cross Abstract: Language models relying on verbalized Chain-of-Thought (CoT) are constrained to token-by-token…