9500 papers
The paper proposes Correctness-Relative Policy Optimization (CoRPO), a modification to Group-Relative Policy Optimization (GRPO) that clips the advantage baseline to a correctness threshold to prevent reinforcing incorrect solutions, thereby significantly improving the model's generalization and cross-domain reasoning capabilities.
This paper proposes SASG-DA, a novel diffusion-based data augmentation framework that leverages semantic guidance and sparse-aware sampling to generate faithful and diverse sEMG data, thereby significantly improving the generalization and performance of myoelectric gesture recognition models on benchmark datasets.
DAP is a compact, discrete-token autoregressive planner that jointly forecasts BEV semantics and ego trajectories with reinforcement learning fine-tuning, achieving state-of-the-art performance on autonomous driving benchmarks despite a limited 160M parameter budget.
This paper proposes Cross-Modal Compositional Self-Distillation (CCSD), a novel framework utilizing a shared-specific architecture and dual self-distillation strategies to achieve robust, state-of-the-art brain tumor segmentation performance across arbitrary missing MRI modality scenarios.
This paper introduces FlashCache, a frequency-domain-guided KV cache compression framework that identifies and preserves critical "Outlier KVs" while leveraging low-pass filtering and dynamic budget allocation to achieve significant inference speedups and memory reduction in multimodal large language models without compromising performance.
This paper presents MambaTAD, an end-to-end one-stage temporal action detection model that leverages a Diagonal-Masked Bidirectional State-Space module and a global feature fusion head to overcome the limitations of existing state-space models and traditional methods in detecting long-span action instances with linear computational complexity.
This paper introduces CycleChemist, a dual-pronged machine learning framework that leverages a new large-scale dataset (OPV2D) to simultaneously predict organic photovoltaic performance and generate synthetically accessible high-efficiency donor-acceptor materials through an integrated predictive and generative approach.
This paper introduces L4L, a solver-centric framework that enhances the trustworthiness of legal AI by integrating role-differentiated LLM agents with SMT-backed formal verification to ensure logical, auditable, and statute-aligned legal reasoning.
This paper demonstrates that language models can be fine-tuned to reliably detect and identify activation steering interventions, revealing that such steering is not inherently undetectable and that models trained to recognize it may paradoxically become more susceptible to behavioral manipulation.
This paper introduces DPAC, a diffusion guidance method that projects adversarial gradients onto the tangent space of iso-density surfaces to minimize path-space KL divergence and control energy, thereby theoretically and empirically achieving higher sample quality (lower FID) while maintaining target classification success.
The paper proposes Deep FlexQP, a deep unfolding-based solver that accelerates nonlinear programming by learning dimension-agnostic parameters for a robust, always-feasible convex QP relaxation, thereby significantly improving the speed and success rates of SQP and safety filter applications while providing rigorous performance guarantees.
The paper introduces Guided Flow Policy (GFP), a novel offline reinforcement learning method that couples a multi-step flow-matching policy with a distilled one-step actor to selectively focus on high-value actions, achieving state-of-the-art performance across diverse benchmarks by overcoming the limitations of indiscriminate behavior regularization.
This paper demonstrates that injecting a canonical action ordering signal into the reward function during RL post-training significantly improves Transformer performance on Zebra puzzles compared to optimizing for task success alone, even when the model is fine-tuned on randomized solution sequences.
This paper proposes a multi-loss learning framework for speech emotion recognition that integrates energy-adaptive mixup and frame-level attention to address data scarcity and emotional complexity, achieving state-of-the-art performance across four benchmark datasets.
This paper introduces a post-training method that induces extreme sparsity in transformer attention (reducing connectivity to ~0.4%) without sacrificing performance, thereby revealing simplified, interpretable task-specific circuits and unifying feature-based and circuit-based perspectives on model behavior.
ClinNoteAgents is a novel LLM-based multi-agent system that effectively predicts and interprets 30-day heart failure readmission risks by transforming unstructured clinical notes into structured risk factors and clinician-style abstractions, offering a scalable and interpretable solution for data-limited healthcare settings.
The paper introduces InternGeometry, an LLM agent enhanced by Complexity-Boosting Reinforcement Learning and a dynamic memory mechanism that iteratively proposes and verifies auxiliary constructions, achieving a medalist-level performance on IMO geometry problems with significantly less training data than previous expert models.
ReFusion introduces a novel masked diffusion model that integrates sequence reorganization with a hybrid parallel-autoregressive decoding strategy to simultaneously achieve full KV cache efficiency, reduce learning complexity, and significantly outperform existing diffusion models while narrowing the performance gap with autoregressive models.
HydroGEM is a self-supervised, zero-shot hybrid TCN-Transformer foundation model that effectively performs continental-scale streamflow quality control by detecting and reconstructing sensor anomalies with high accuracy and cross-national generalization, thereby addressing the scalability limitations of manual hydrological data validation.
This paper introduces RePo, a novel mechanism that leverages a differentiable module to dynamically re-position tokens based on contextual dependencies rather than fixed linear indices, thereby reducing extraneous cognitive load and enhancing LLM performance on tasks involving noisy contexts, structured data, and long-range dependencies.