Related papers: When to Commit? Towards Variable-Size Self-Contain…

Modern large language model (LLM) inference engines optimize throughput and latency under fixed decoding rules, treating generation as a linear progression in token time. We propose a fundamentally different paradigm: entropic\-time…

The emergence of Large Language Models (LLMs) has driven rapid progress in multi-modal learning, particularly in the development of Large Vision-Language Models (LVLMs). However, existing LVLM training paradigms place excessive reliance on…

Diffusion-based large language models (dLLMs) have recently gained significant attention for their exceptional performance and inherent potential for parallel decoding. Existing frameworks further enhance its inference efficiency by…

Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs) through increased test-time computation. Current state-of-the-art methods often employ computationally intensive reward models…

Multi-modal large language models (MLLMs) have achieved remarkable capabilities by integrating visual perception with language understanding, enabling applications such as image-grounded dialogue, visual question answering, and scientific…

Block discrete diffusion language models factorize a sequence autoregressively over fixed-size positional blocks, decoupling within-block parallel denoising from across-block conditioning. We argue that this rigid partition wastes structure…

Diffusion-based large language models (dLLMs) have exhibited substantial potential for parallel text generation, which may enable more efficient generation compared to autoregressive models. However, current dLLMs suffer from fixed…

Diffusion Language Models (DLMs) present a promising non-sequential paradigm for text generation, distinct from standard autoregressive (AR) approaches. However, current decoding strategies often adopt a reactive stance, underutilizing the…

Large language models (LLMs) have shown promising performance across diverse domains. Many practical applications of LLMs, such as code completion and structured data extraction, require adherence to syntactic constraints specified by a…

Long-sequence decision-making, which is usually addressed through reinforcement learning (RL), is a critical component for optimizing strategic operations in dynamic environments, such as real-time bidding in computational advertising. The…

While Vision-Language Models (VLMs) have shown remarkable abilities in visual and language reasoning tasks, they invariably generate flawed responses. Self-correction that instructs models to refine their outputs presents a promising…

The prevailing assumption of an exponential decay in large language model (LLM) reliability with sequence length, predicated on independent per-token error probabilities, posits an inherent limitation for long autoregressive outputs. Our…

Recent byte-level language models (LMs) match the performance of token-level models without relying on subword vocabularies, yet their utility is limited by slow, byte-by-byte autoregressive generation. We address this bottleneck in the…

Self-consistency has emerged as a powerful method for improving the accuracy of short answers generated by large language models. As previously defined, it only concerns the accuracy of a final answer parsed from generated text. In this…

The iterative denoising paradigm of Diffusion Large Language Models (DLMs) endows them with a distinct advantage in global context modeling. However, current decoding strategies fail to leverage this capability, typically exhibiting a local…

Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density. This token-uniform regime wastes capacity on locally predictable spans while under-allocating…

Self-conditioning has been central to the success of continuous diffusion language models, as it allows models to correct previous errors. Yet its ability degrades precisely in the regime where diffusion is most attractive for deployment:…

Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive models. Controlled generation methods for DLMs, imported from autoregressive models, apply…

Variable-length feedback coding has the potential to significantly enhance communication reliability in finite block length scenarios by adapting coding strategies based on real-time receiver feedback. Designing such codes, however, is…

While multimodal fusion has been extensively studied in Multimodal Sentiment Analysis (MSA), the role of fusion depth and multimodal capacity allocation remains underexplored. In this work, we position fusion depth, scalability, and…