AIQB
ResearchOrdinary

本周最佳Research：Story Imprinting 与 JEPA-Anything

Source: X：马东锡 NLP (@dongxi_nlp)·
Original title: 本周最佳两篇 Week 38 Story Imprinting： AI Assistants Absorb Traits from Human Characters They Resemble …

Summary

本周最佳两篇 Week 38 Story Imprinting： AI Assistants Absorb Traits from Human Characters They Resemble JEPA-Anything： Learning Predictive Models across Different Worlds Story Imprinting https://arxiv.org/pdf/2609.10883 JEPA-Anything https://arxiv.org/pdf/2609.20800
CategoryAI Research & Papers
TierOrdinary
Published
Indexed by AIQB
SourceX：马东锡 NLP (@dongxi_nlp)
AIQB record IDintel-9657f54aeb678c0c71af691f
Read original source ↗View data sourceMore Research

Related stories

Matched by category, entity tags and source

ResearchOrdinary
Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation
Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way now operate robots without robot-specific training.Whether this paradigm is …
Source: arXiv
ResearchOrdinary
Embedding Models Measure in Peculiar Ways
Embedding spaces define notions of semantic similarity and distance. We study whether those embeddings reflect physical measurements of mass, distance, time and volume, which admit a unique, objective notion of semantic equivalence and dis…
Source: arXiv
ResearchOrdinary
Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision
Complex robotic manipulation tasks frequently require a long-term memory of past events and actions. As conditioning on full histories renders policies prone to spurious correlations and degrades performance, many approaches to policy memo…
Source: arXiv
ResearchOrdinary
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence. Most feed-forward methods infer articulation from a single observation and therefore rely h…
Source: arXiv
ResearchOrdinary
Paint-Anything: Unified Any-Color Control for Image Generation and Editing
Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored color generation, editing, and colorization, but often reli…
Source: arXiv
ResearchOrdinary
ERCPMP-Gx: Endoscopic Image and Video Dataset for Morphological, Histopathological, and Genomic Characterization of Colorectal Polyposis
Hereditary polyposis syndromes can be precursor lesions to colorectal cancer and are associated with a broad spectrum of extracolonic tumors. Early identification and accurate classification of these syndromes are essential for timely diag…
Source: arXiv
ResearchOrdinary
How Does Distribution Shift Shape Pretraining Gains in Neural PDE Surrogates?
Pretraining a neural PDE surrogate can reduce the amount of new CFD data needed when geometry or modeled physics changes. However, it remains unclear how different components of distribution shift affect this benefit. We pretrain a surroga…
Source: arXiv
ResearchOrdinary
Quantifying Overclaiming Propensity in Frontier LLM Agents
Frontier coding agents are increasingly trusted to work autonomously for long periods, yet an agent's final response is often the only account of that work a user sees. We quantify the propensity of frontier agents to \emph{overclaim} task…
Source: arXiv
ResearchOrdinary
Unifying Models of Intergroup Hostility in Online Discourse
Hostile rhetoric toward social groups can normalize exclusion and justify mistreatment, as well as contribute to rising polarization and political violence. Efforts to moderate hostile rhetoric in online speech draw on foundational theorie…
Source: arXiv
ResearchOrdinary
Score Centering Stabilizes Off-policy Reinforcement Learning
Reinforcement learning (RL) of large language models is notoriously sensitive to small differences between training and inference engines, often referred to as the training-inference mismatch (TIM). However, completely eliminating TIM is i…
Source: arXiv