1072 papers
This paper introduces Aura, a universal framework that enhances aviation time series forecasting by explicitly encoding and integrating three distinct types of multi-dimensional exogenous factors through a tailored tripartite mechanism, achieving state-of-the-art performance on large-scale industrial datasets.
This paper introduces ARC-TGI, an open-source framework featuring human-validated Python generators that produce diverse, rule-consistent ARC-AGI tasks with natural language reasoning chains and code, addressing dataset overfitting by ensuring training examples collectively reveal underlying rules for scalable benchmarking.
This study reveals that SpeechLLMs inherit significant redundancy from their pretrained LLM decoders, demonstrating that pruning up to 40% of decoder layers maintains strong performance across ASR and translation tasks while enabling a single, efficient backbone for multi-task deployment.
This paper proposes LBM, a hierarchical large auto-bidding model that integrates a reasoning-based LLM-Think module with an action-generating LBM-Act module, utilizing a dual embedding mechanism and offline reinforcement fine-tuning (GQPO) to overcome hallucinations and improve bidding performance in dynamic ad auctions.
This paper theoretically and empirically demonstrates that analogical reasoning in transformers emerges from a unified mechanism where entities with similar properties are encoded into aligned representations, a capability that depends critically on specific training curricula and the explicit inclusion of identity bridges in the data.
This paper introduces C2-Faith, a benchmark derived from PRM800K that evaluates LLM judges on their ability to assess causal and coverage faithfulness in chain-of-thought reasoning, revealing that their performance varies significantly by task and that they struggle to localize errors or accurately score incomplete reasoning.
This paper introduces Sparse-BitNet, a unified framework demonstrating that 1.58-bit BitNet models are inherently more compatible with semi-structured N:M sparsity than full-precision models, enabling stable training, reduced performance degradation, and significant speedups in both training and inference.
This paper proposes a systematic framework for annotating and visualizing legal argumentation structures in Chinese judicial decisions by defining four proposition types and five relational types to enable consistent, reproducible computational analysis of judicial reasoning.
This paper introduces a general framework for deriving new language models by composing pretrained models with deterministic finite-state transducers, enabling efficient probability marginalization and conditioning to adapt outputs to diverse formats like bytes, words, or amino acids without retraining.
This paper demonstrates that diffusion LLMs enhance their reasoning capabilities by utilizing end-of-sequence (EoS) tokens as a hidden scratchpad for intermediate computations, a hypothesis confirmed through behavioral experiments and causal interventions showing that manipulating these tokens directly alters the model's output.
This paper proposes a novel framework that distills the geometric semantics of Signal Temporal Logic into a Transformer encoder via kernel alignment, enabling efficient, invertible, and semantically faithful neural representations that overcome the computational limitations of symbolic kernels and the structural deficiencies of syntax-based embeddings.
This paper proposes a deterministic and efficient GraphRAG framework that replaces non-reproducible Leiden clustering with k-core decomposition and lightweight heuristics to improve global sensemaking, answer comprehensiveness, and diversity while reducing token costs across diverse real-world datasets.
This paper proposes a vocabulary trimming strategy for speculative decoding that formulates draft model vocabulary selection as a constrained optimization problem to balance token coverage and latency, achieving significant throughput improvements and latency reductions by tailoring the vocabulary to domain-specific workloads.
This paper introduces VietJobs, the first large-scale public corpus of 48,092 Vietnamese job advertisements, and benchmarks generative large language models on tasks like job classification and salary estimation to advance Vietnamese NLP and labor market analytics.
This paper introduces the Multilingual Cloud Corpus, the first national-scale, parallel, multimodal dataset for Bangladesh's predominantly oral and endangered minority languages, which was systematically collected through extensive fieldwork and is now publicly available to advance digital preservation and low-resource natural language processing.
SarcasmMiner is a reinforcement learning-based post-training framework that employs a dual-track distillation strategy with a generative reward model and group relative policy optimization to significantly enhance robust audio-visual sarcasm reasoning and reduce hallucinations in foundation models.
This paper establishes a formal geometric framework linking AI debate and RLAIF by demonstrating that the value of debate scales with knowledge divergence between models, transitioning from negligible benefit to essential oversight as representations diverge, while identifying specific regimes where debate unlocks inaccessible outcomes or risks coordination failure.
WavSLM is a single-stream speech language model that achieves competitive speech generation and consistency without text supervision by quantizing and distilling WavLM representations into a single codebook for autoregressive next-chunk prediction.
The paper introduces Med-V1, a family of efficient 3-billion-parameter small language models trained on synthetic data that achieve performance comparable to frontier models like GPT-5 for biomedical evidence attribution and hallucination detection, while enabling scalable applications such as analyzing citation validity and identifying evidence misattributions in clinical guidelines.
This paper introduces PersianPunc, a large-scale dataset of 17 million samples, and a fine-tuned ParsBERT model that achieves a 91.33% macro-averaged F1 score for Persian punctuation restoration, offering a more efficient and accurate alternative to large language models for real-time applications.