FedTSV: Fairness-Aware Federated Learning via Trajectory Shapley Value
This paper introduces the Trajectory Shapley Value (TSV), a contribution metric that evaluates each federated learning client's influence on the global model's optimization trajectory using validation-based, temporally consistent utility. Building on TSV, the authors propose FedTSV, an adaptive aggregation method that converts per-round evaluations into dynamic client weights to handle heterogeneous and adversarial participation. Experiments on benchmark datasets demonstrate improved convergence speed, robustness, and equitable contribution assessment compared to fixed-weight aggregation baselines.
Related guides (2)
Related events (8)
IntraShuffler: Privacy-Preserving Framework for Heterogeneous DP Federated Learning
This paper identifies a novel Privacy Inference Attack against heterogeneous differential privacy federated learning (HDP-FL) systems, where an honest-but-curious server exploits epsilon-aware aggregation and gradient denoising to infer client data distributions and link updates across rounds. To counter this, the authors propose IntraShuffler, a middleware framework that groups clients into privacy-compatible buckets and performs parameter-level shuffling within buckets, preserving epsilon-aware aggregation while disrupting persistent gradient structure. Experiments on four datasets show IntraShuffler reduces gradient recoverability by over 60% and drops surrogate inference accuracy from 0.78 to 0.33 with minimal utility loss.
TrajTok: Adaptive Spatial Tokenization for Trajectory Representation Learning
TrajTok is a trajectory encoder that learns transferable GPS trace representations via multi-resolution hexagonal spatial tokenization and masked-token pretraining. It uses a factorized transformer with per-modality self-attention, cross-attention fusion, and spatiotemporal rotary position embeddings (ST-RoPE) to jointly encode geometry and kinematics. A single frozen TrajTok encoder with lightweight adapters outperforms task-specific methods on trajectory similarity search, classification, ETA, and travel-time regression on the Porto dataset. The work positions learned spatial tokenization plus masked pretraining as a viable path toward general-purpose trajectory foundation models.
Taiji: Pareto Optimal Policy Optimization for LLM-enhanced recommendation at Kuaishou scale
Researchers from Kuaishou present Taiji, an LLM-as-Enhancer framework for industrial recommender systems that addresses two bottlenecks: generating high-quality chain-of-thought data via reverse-engineered reasoning and rejection sampling during SFT, and balancing semantic vs. ID-based rewards during RL alignment via a new algorithm called Pareto Optimal Policy Optimization (POPO). The system has been deployed on Kuaishou's advertising platform since May 2026, serving over 400 million daily users. The paper contributes both a practical deployment case study and a novel RL alignment technique for the LLM4Rec paradigm.
Bradley-Terry model proposed for fairer ranking of recommendation algorithms across dataset types
A new arXiv preprint introduces a Bradley-Terry (BT) model-based methodology for ranking recommendation algorithms in a way that accounts for dataset characteristics such as sparsity, sequential structure, and scale. The authors argue that naive metric aggregation (e.g., averaging NDCG) produces misleading rankings and propose BT trees and covariate-extended BT models as alternatives. The framework also enables ranking predictions on unseen datasets without running the models, and includes a new metric for ranking consistency.
Q-target framework unifies supervised fine-tuning variants through target distribution design
A new arXiv preprint reframes supervised fine-tuning (SFT) as a problem of target distribution design rather than loss objective selection, introducing the Q-target framework that decomposes SFT supervision into two explicit choices: reliance on the observed token and allocation of remaining probability mass. The authors show that many existing SFT variants can be understood as implicit choices of this target distribution. They propose Target-SFT, which constructs training objectives directly from the desired target distribution, and report consistent improvements across ten reasoning dataset-model settings. The work offers a unifying theoretical lens and opens a broader design space for SFT objectives.
Tracking Behavioral Trajectories of Adapting Agents via Trait Vectors in Embedding Space
This paper introduces a methodology for measuring behavioral traits of AI agents by defining traits as directions in the embedding space of a text embedding model, trained on labeled diffs of agent skill/memory/configuration files. A linear model achieves 91.2% sign classification accuracy and Spearman ρ=0.82 on detecting propensity to seek sensitive data across 68 labeled skill diff pairs. The framework extends to an agent-to-agent evaluation protocol where one agent can assess another's skill file updates through a trusted intermediary, enabling ongoing behavioral monitoring of self-modifying agents.
Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL
Hugging Face introduces Delta Weight Sync in TRL, a technique for efficiently synchronizing model weight updates during large-scale training by transmitting only the delta (difference) between checkpoints rather than full parameter snapshots. The approach targets trillion-parameter training regimes where checkpoint bandwidth is a significant bottleneck. The post describes integration with the Hugging Face Hub as a storage and distribution layer for these delta updates.
HullFT: Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching
HullFT is a new method for test-time finetuning (TTFT) of language models that addresses the dual bottlenecks of retrieval quality and per-query finetuning cost. It represents query embeddings as sparse convex combinations of training sequences using Frank-Wolfe optimization, yielding diverse and relevant support sets without expensive diversity-aware search. A geometric integerization step converts fractional weights into integer multiplicities, enabling a Gradient Reuse scheme that amortizes forward-backward computation across repeated examples. Experiments show improved quality-efficiency tradeoffs over prior TTFT methods, measured in bits-per-byte at lower total runtime.