The paper proposes a novel multimodal framework for session-based music recommendation that jointly models audio, lyric, and semantic content signals within a unified LLM-based sequential reasoning sy…

ElasticMem introduces a novel framework that treats memory as an elastic latent resource, allowing LLM agents to adaptively manage and inject variable-budget memories for improved performance in long-…

The paper introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…

V-LynX is a framework that enhances Video LLMs by integrating new modalities into their existing token interface, achieving state-of-the-art performance across diverse video understanding tasks.

CoHyDE introduces an iterative co-training framework that jointly optimizes an LLM rewriter and a dense encoder, significantly improving tool retrieval accuracy for LLM agents, especially on vague que…

The paper demonstrates that the AI-like style introduced by post-training alignment can be measured, localized, and causally removed using a novel ablation technique called PASTA.

The paper introduces Partial Information Decomposition (PID) to quantitatively separate unique, redundant, and synergistic contributions of different modalities (e.g., vision, language) in multimodal…

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 DOMINO, a novel inductive framework that synthesizes domain-specific data for LLMs using only reference examples, significantly improving performance on challenging, implicitly de…

The paper proposes SubFit, a novel compression technique that achieves superior LLM compression by replacing non-contiguous, submodule-level components (Attention and FeedForward) with lightweight res…

SPARQLe is a hardware-software co-design framework that exploits the inherent sub-precision sparsity of LLM activations to reduce memory traffic and enable efficient computation on lower-bit datapaths…

The paper proposes using fine-grained quality signals, such as pairwise self-judgments and token-level entropy, instead of simple binary correctness to improve LLM performance on saturated datasets, s…

UniAudio-Token is a framework that enhances existing semantic speech tokenizers with general audio perception, allowing them to handle diverse audio types while maintaining high-fidelity speech capabi…

The paper introduces Single-stage Sparse Retrieval (SSR), a method that replaces computationally expensive vector clustering with sparse autoencoding to achieve highly efficient multi-vector retrieval…

The paper proposes InSemRAG, an enhanced RAG framework that improves retrieval accuracy and knowledge integrity by incorporating intent-aware retrieval and semantics-preserving chunking, achieving sta…

This paper evaluates the causal reasoning abilities of large language models and finds that they rely heavily on lexical pattern matching rather than structural reasoning.