2384 papers
NasoVoce is a nose-mounted speech interface that fuses acoustic and vibration signals to enable robust, discreet, and always-available voice interaction for AI, effectively overcoming the limitations of existing silent and whispered speech recognition methods.
PC-Diffuser is a safety augmentation framework that integrates a certifiable, path-consistent capsule barrier function directly into the denoising loop of diffusion-based trajectory planners to ensure forward invariance and dynamically feasible motion while preserving the learned path geometry.
This paper presents the first systematic comparison of fairness between reasoning and non-reasoning rerankers, finding that reasoning models neither improve nor harm fairness compared to traditional approaches, as they largely preserve the fairness characteristics of their input rankings.
This paper introduces Concept-Gated Visual Distillation (CGVD), a training-free, model-agnostic inference framework that overcomes the "Precision-Reasoning Gap" in Vision-Language-Action models by parsing instructions to identify distractors and using Fourier-based inpainting to generate clean observations, thereby significantly improving robotic manipulation success rates in highly cluttered environments.
This paper introduces FairFAL, an adaptive federated active learning framework that leverages lightweight prediction discrepancy and prototype-guided pseudo-labeling to dynamically select between global and local query models, effectively addressing the challenges of extreme non-IID data and global class imbalance to achieve superior performance over state-of-the-art methods.
This paper introduces DIBJudge, a robust fine-tuning framework that mitigates translationese bias in multilingual LLM-as-a-Judge systems by using a disentangled information bottleneck to isolate spurious cross-lingual correlations from judgment-critical representations.
This paper introduces GenCC, a framework that leverages large language models to automatically design optimized congestion control utility functions, achieving performance improvements of 37% to 142% over state-of-the-art protocols by utilizing generative code evolution or mathematical chain-of-thought strategies.
HEAL is an RL-free distillation framework that overcomes the "Teacher Ceiling" of standard rejection sampling by synergizing entropy-guided repair, uncertainty filtering, and progressive curriculum learning to transfer reasoning capabilities from Large Reasoning Models to smaller students.
This paper proposes a dynamic knowledge fusion framework for multi-domain dialogue state tracking that addresses challenges in modeling dialogue history and data scarcity by using a contrastive learning-based encoder to select relevant slots and leveraging their structured information as contextual prompts to improve tracking accuracy and generalization.
This paper proposes a more efficient and effective paradigm for Generative Recommender Systems by replacing the standard interleaving of item and action tokens with two novel architectures, AttnLFA and AttnMVP, which explicitly model causal item-action dependencies to reduce sequence complexity, lower training costs, and improve recommendation performance.
This paper proposes a scalable and interpretable framework for few-shot robotic adaptation to non-stationary environments that estimates a low-dimensional, temporally regularized "Trend ID" via backpropagation while keeping model parameters fixed, thereby avoiding catastrophic forgetting and high computational costs.
This mixed-methods study introduces the concept of "Reactive Writing," revealing that co-writing with AI shifts the process from traditional ideation to an evaluation-first approach where writers unconsciously adopt AI-suggested ideas and opinions while maintaining an illusion of full control.
This paper introduces Causal Concept Graphs (CCG), a framework that combines task-conditioned sparse autoencoders with differentiable structure learning to map causal dependencies between interpretable latent features in LLMs, demonstrating through the Causal Fidelity Score that graph-guided interventions significantly enhance stepwise reasoning performance compared to existing tracing and random baselines.
This paper establishes a new scaling law for Mixture-of-Experts models by deriving an explicit power-law formula for the optimal compute allocation ratio between expert and attention layers, enabling more efficient model design under fixed computational budgets.
The paper introduces TRACED, a novel framework that evaluates LLM reasoning reliability by modeling reasoning traces as geometric trajectories, where correct reasoning is identified by high-progress, stable paths while hallucinations are characterized by low-progress, unstable patterns, thereby bridging geometric kinematics with cognitive concepts like hesitation and certainty.
This paper presents a novel probabilistic safe control framework for human-robot interaction that integrates control barrier functions with conformal risk control to provide formal safety guarantees, dynamically adjust safety margins based on interaction context, and significantly reduce collision rates while maintaining task efficiency.
This paper proposes novel prompt-based techniques grounded in imprecise probabilities to effectively elicit and quantify both first-order and second-order uncertainty from large language models, thereby addressing systematic failures in ambiguous or complex settings and improving the credibility of their uncertainty reporting.
This paper analyzes the learning dynamics of two-layer over-parameterized linear networks under label noise SGD, revealing a two-phase process where noise drives the transition from the lazy to the rich regime to improve generalization, a mechanism that also extends to Sharpness-Aware Minimization (SAM).
This paper introduces PP-LUCB, a cost-efficient algorithm that optimally combines biased LLM-generated proxy scores with selective human audits to identify the best service system configuration while providing statistically valid confidence guarantees and significantly reducing audit costs.
The paper introduces STemDist, the first dataset distillation method designed for spatio-temporal forecasting that simultaneously compresses both spatial and temporal dimensions through a hybrid cluster-level and subset-based approach, achieving significantly faster training, reduced memory usage, and lower prediction errors compared to existing methods.