The paper demonstrates that positional encodings are not necessary for transformers to achieve universal computation, showing that the inherent mechanism of sliding context windows already provides su…

The paper introduces Drifting Preference Optimization (DrPO), an efficient online method for preference finetuning one-step text-to-image generators that avoids complex gradient calculations and model…

The paper introduces a history-dependent bias to generative protein emulators, significantly improving the exploration of rare and diverse protein states compared to standard emulators.

EvoMD-LLM introduces a novel framework that models reactive molecular dynamics as a symbolic temporal language problem, enabling LLMs to accurately predict complex, time-evolving chemical processes.

The paper introduces a framework for composing deep probabilistic models using five specific factor-graph primitives that guarantee closed-form variational inference, thereby preserving tractability i…

EvoGens is an evolution-inspired framework that treats scientific idea generation as an evolutionary search, significantly boosting the novelty and diversity of generated research ideas compared to ex…

The paper introduces BlockGen, a blockwise sequence model, to investigate the performance of uniform-state versus masked diffusion models when generating sequences block-by-block, showing that the per…

The paper analyzes language generation and identification in the limit under bounded memory, showing that memory constraints significantly alter learnability, particularly affecting achievable density…

The paper proposes EPIC, an efficient and parallel decoding framework that significantly speeds up the process of constraining diffusion language model outputs using Context-Free Grammars (CFG).

The paper proposes a novel probabilistic globally constrained decoding (P-GCD) method that efficiently constructs proposals for locally constrained decoding, significantly improving convergence speed…

The paper argues that using confidence-based decoding, which is optimized via training mask alignment, fundamentally misaligns Masked Diffusion Models (MDMs) from the logical flow needed for complex r…

The paper introduces GeoCoupling, a framework that systematically optimizes the temporal coupling between heterogeneous modalities to improve the co-design of biomolecules, outperforming fixed synchro…

The paper introduces AMix-2, a novel protein-text foundation model that unifies protein understanding and sequence design by embedding both modalities in a shared token space, achieving state-of-the-a…

The paper introduces Q-ALIGN DT, a novel framework that improves conditioned sequence models by enforcing alignment between the input return-to-go (RTG) signal and the output policy's expected Q-value…

The paper proposes explicitly disentangling positional and semantic representations in Transformer encoders, demonstrating that this separation allows for a clearer understanding of how positional inf…

The paper proposes an efficient inference procedure for generative planning models by modifying the Open-Closed List (OCL) search, achieving superior performance over existing baselines.

The paper introduces Expected Value Alignment (EVA), a novel reward modeling procedure that allows continuous scoring of intermediate reasoning steps in formal mathematics verification while maintaini…

The paper introduces FTDiff, a reinforcement learning fine-tuning framework that efficiently generates high-quality, drug-like molecules constrained by a target protein structure, outperforming existi…

The paper analyzes order-agnostic language models (OALMs), finding that their learned conditionals are not true factorizations and proposing a variance-based diagnostic to compare the quality of diffe…