This paper introduces Bifocal dLLMs (R2LM), a new paradigm for discrete diffusion language models that combines causal and bidirectional attention for improved throughput and generation quality.

The paper proposes AsyMoE, a novel Mixture of Experts architecture for Large Vision-Language Models that explicitly models the inherent asymmetry between visual and linguistic modalities, achieving si…

The authors redesigned the symbolic backend of a SLOG test system using CCG directed types and achieved better performance than the previous SOTA.

The paper proposes Fresco, a novel bidirectional type inference approach for first-class polymorphism that enables local type information to flow back and forth between functions and arguments.

This paper introduces a Hybrid Mixture-of-Experts (HybridMoE) framework and a specialized corpus (Varnika) to significantly improve language models' ability to understand and retain figurative, cultur…

The paper introduces MIDI, a novel multilingual dataset that embeds idioms in realistic sentence and conversational contexts across diverse resource levels, revealing that idiom comprehension is signi…

This paper proposes a context engineering approach that scales memory with distinct information instead of tokens, using a novelty-gated cache and state-space summary.

The paper introduces ASK-NN, an asymmetric two-sample test for detecting hallucinations in LLM-generated outputs based on the directed k-nearest-neighbor graph.

The paper introduces the Safety Asymmetry Score (SAS) to measure how a model's vulnerability to adversarial content changes based on whether the malicious input arrives via the user message, tool meta…

The paper introduces the Safety Asymmetry Score (SAS) to measure how a model's susceptibility to adversarial attacks changes based on whether the malicious content arrives via the user message, tool m…

The paper demonstrates that audio-language models often ignore conflicting audio evidence in favor of text, and proposes a training-free decoding rule, GACL, that significantly improves faithfulness b…

This paper tests the assumption that evaluation is easier than generation in LLM-as-a-Judge and self-evaluation pipelines using a controlled in-context QA setting and reveals that evaluation attends t…

This paper introduces DDC, a Dead-Direction Conditioner that keeps a deep network's optimization on the symmetry quotient by conditioning the optimizer's state in the orbit decomposition of a $G$-inva…

The paper proposes a dual-interventional framework to characterize how linguistic structures and contextual cues influence LLMs' spatial reasoning for navigation, finding that topological information…

This paper introduces a new way to represent finite posets as subwords of finite words in categories, and characterizes the monic categories that admit this representation.

The paper introduces ERGeoBench, a comprehensive diagnostic benchmark designed to evaluate the fine-grained capabilities of multimodal large language models (MLLMs) for embodied geo-localization acros…

The paper proposes Resonant Context Anchoring (RCA), a lightweight, training-free method that enhances factual faithfulness in LLMs by dynamically amplifying the signal of external context evidence du…

The paper provides a formal statistical and conceptual framework for defining and measuring 'pairwise reference alignment,' which quantifies how well a model's scoring function agrees with a given ref…

This paper presents an efficient algorithm for right-to-left sequence prediction based on a new complexity measure called arithmetic repetition complexity, and demonstrates its application to predicti…

The paper introduces a diagnostic framework to decompose multilingual LLM performance variance, showing that language identity and model-benchmark interactions are key drivers of performance gaps.