Claims Browser

The orthogonality among principal subspaces of the Fisher information matrix's K-FAC approximation, estimated from a small number of downstream task samples, can reflect the similarity between different tasks in pre-trained models

"a key observation about the Fisher information matrix (FIM) of pre-trained models: the orthogonality among the principal subspaces of its Kronecker-Factored Approximate Curvature (K-FAC) approximation, estimated from a small number of downstream task samples, can reflect the similarity between different tasks."

FiUni can effectively infer latent batch-level task affiliations and achieve competitive performance against advanced task-aware continual learning methods with fewer trainable parameters

"Experiments show that FiUni can effectively infer latent batch-level task affiliations and achieve competitive performance against advanced task-aware CL methods with fewer trainable parameters."

FiUni's approach of constructing FIM-derived frozen subspaces to guide low-rank adaptation while matching Fisher principal subspaces enables adaptive determination of whether to reuse knowledge, expand subspaces, or create new ones, dynamically balancing knowledge sharing and task isolation

"FiUni constructs FIM-derived frozen subspaces to guide low-rank adaptation (LoRA), while matching the Fisher principal subspace of each incoming batch window with historical subspaces. This enables FiUni to adaptively determine whether to reuse existing knowledge, expand a related subspace, or create a new subspace, dynamically balancing knowledge sharing and task isolation."

Emotions play an important functional role in regulating the relative priorities of competing goals in decision-making agents under changing external environments and evolving internal states

"Under changing external environments and evolving internal states, emotions play an important functional role in regulating the relative priorities of competing goals."

Preference regulation in decision-making agents can be computationally realized through reinforcement learning based on goal-directed theory of emotion

"Inspired by the goal-directed theory of emotion, this paper studies how such preference regulation can be computationally realized through reinforcement learning."

High-level goals can autonomously induce state-dependent preferences over competing lower-level objectives through emergent emotional preference

"We first propose a conception of emergent emotional preference: a high-level goal autonomously induces state-dependent preferences over competing lower-level objectives."

The optimality gap in preference-regulated agent policies vanishes when the optimal policy can be represented by available preference-conditioned policies

"We show that the gap vanishes when the optimal policy can be represented by the available preference-conditioned policies."

Learned preference functions in multi-objective environments exhibit contextual priority switching, graded trade-offs, and temporal persistence, outperforming fixed-preference and handcrafted-preference strategies

"Experiments in self-constructed multi-objective exploration environments show that the learned preference function exhibits contextual priority switching, graded trade-offs, and temporal persistence, and outperforms the evaluated fixed-preference and handcrafted-preference strategies."

Existing video diffusion model methods for image-to-scene generation rely on incomplete conditioning signals, leading to stochastic hallucinations, long-term drifts and suboptimal 3D consistency

"Existing methods based on video diffusion model (VDM) commonly rely on incomplete conditioning signals such as sparse point clouds or 2D panoramas, leading to stochastic hallucinations, long-term drifts and suboptimal 3D consistency."

SpatialCrafter outperforms state-of-the-art methods for explorable image-to-scene generation and mitigates long-term drift while remaining robust under rapid camera motion and extreme viewpoint changes

"Extensive experiments on both synthetic and real-world datasets show that SpatialCrafter outperforms state-of-the-art methods, mitigates long-term drift, and remains robust and consistent under rapid camera motion and extreme viewpoint changes."

Using a global 3D proxy with Point-anchored Sparse Structure Flow enables spatially aligned and geometrically consistent 3D proxy generation for high-fidelity image-to-scene generation

"we propose a Point-anchored Sparse Structure~(PaSS) Flow module that predicts a spatially aligned and geometrically consistent 3D proxy"

Google DeepMind is conducting the world's first double-blind AI evaluations

"Piloting the world's first double-blind AI evaluations"

OpenAI's Jalapeño chip will start deploying by year-end

"It starts deploying by year-end."

Nvidia is acquiring Hugging Face for $12.9 billion

"Nvidia is buying Hugging Face for $12.9B (via The Information)."

Quotient couplings can be lifted to aligned representatives without additional cost

"quotient couplings can be lifted to aligned representatives without additional cost"

Structure-aware couplings substantially improve sample quality at small integration budgets in graph and molecular generation

"these structure-aware couplings substantially improve sample quality at small integration budgets"

The proposed molecular models remain competitive under conventional many-step sampling when scaled up

"our scaled-up molecular models remain competitive under conventional many-step sampling"

ClusterAttention is a general training-free speedup method for bidirectional attention layers that uses fast recursive clustering adapting to the geometry of keys and queries

"This paper introduces ClusterAttention, a general training-free speedup of bidirectional attention layers. Existing sparse attention methods either rely on structure in the input, such as order in language or spatial proximity in images, or use slow clustering processes amortized over several forward passes. ClusterAttention instead uses a fast recursive clustering method that adapts to the geometry of the keys and queries in each attention head to produce useful clusters."