25 accepted papers
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key ingredient for unlocking complex reasoning capabilities in large language models. Recent work ProRL \citep{liu2025prorl} has shown promise in scaling RL by increasing the number of training steps. However, performance plateau…
Although Reinforcement Learning with Verifiable Rewards (RLVR) has become an essential component for developing advanced reasoning skills in language models, contemporary studies have documented training plateaus that emerge following thousands of optimization steps, demonstrating notable decreases…
Current chemical large language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) to solve complex reasoning problems. However, forcing nonverbal tacit chemical logic into discrete natural language imposes a fundamental ``modality mismatch,'' creating an artificial bottleneck for r…
Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models (LLMs) with human preferences. However, reward-based methods built on the Bradley–Terry assumption struggle to capture the non-transitive and heterogeneous nature of real-world p…
Recently, significant progress has been made in protein-ligand docking, especially in deep learning methods, and some benchmarks were proposed, such as PoseBench and PLINDER. However, these studies typically focus on the self-docking scenario, which is less practical in real-world applications. More…
Recent advances in generative diffusion and flow-matching models have revolutionized molecular design, enabling the creation of novel proteins, small molecules, and RNA sequences with unprecedented fidelity. Yet, these models remain intuitive rather than intelligent—they generate without reasoning. …
Accurate RNA structure modeling remains difficult because RNA backbones are highly flexible, non-canonical interactions are prevalent, and experimentally determined 3D structures are comparatively scarce. We introduce RiboSphere, a framework that learns discrete geometric representations of RNA by c…
Large Language Models (LLMs) with extended context lengths face significant computational challenges during the pre-filling phase, primarily due to the quadratic complexity of self-attention. Existing methods typically employ dynamic pattern matching and block-sparse low-level implementations. Howev
Molecular dynamics (MD) has long been the de facto choice for simulating intricate physical systems from first principles. Recent efforts utilize the implicit neural representation (INR) to directly learn surface point clouds' signed distance function (SDF) with promising outcomes. However, INR's te…
Protein-protein interactions (PPIs) are governed by surface complementarity and hydrophobic interactions at protein interfaces. However, designing diverse and physically realistic protein structure and surfaces that precisely complement target receptors remains a significant challenge in computation…
Large language models (LLMs) have demonstrated remarkable capabilities across various domains, yet their application to relational deep learning (RDL) remains underexplored. Existing approaches adapt LLMs by traversing relational links between entities in a database and converting the structured dat…
Code localization–identifying precisely where in a codebase changes need to be made–is a fundamental yet challenging task in software maintenance. Existing approaches struggle to efficiently navigate complex codebases when identifying relevant code snippets.The challenge lies in bridging natural lan…
Accurate estimation of mutational effects on protein-protein binding energies is an open problem with applications in structural biology and therapeutic design. Several deep learning predictors for this task have been proposed but, presumably due to the scarcity of binding data, these methods under-…
Machine learning (ML) enables accurate and fast molecular property predictions, which is of interest in drug discovery and material design. Their success is based on the principle of similarity at its heart, assuming that similar molecules exhibit close properties. However, activity cliffs challenge…
The integration of sentences poses an intriguing challenge within the realm of NLP, but it has not garnered the attention it deserves. Existing methods that focus on sentence arrangement, textual consistency, and question answering have been shown to be inadequate in addressing this issue. To bridge…
Machine learning catalyzes a revolution in chemical and biological science. However, its efficacy is heavily dependent on the availability of labeled data, and annotating biochemical data is extremely laborious. To surmount this data sparsity challenge, we present an instructive learning algorithm n…
Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias. However, existing pseudo-label selection strategies are limite…
Molecular surfaces imply fingerprints of interaction patterns between proteins. However, non-equivalent efforts have been paid to incorporating the abundant protein surface information for analyzing proteins' biological functions in juxtaposition to amino acid sequences and 3D structures. We propose…
Therapeutic antibodies are an essential and rapidly flourishing drug modality. The binding specificity between antibodies and antigens is decided by complementarity-determining regions (CDRs) at the tips of these Y-shaped proteins. In this paper, we propose a \textbf{h}ierarchical \textbf{t}raining…
Masked image modeling, an emerging self-supervised pre-training method, has shown impressive success across numerous downstream vision tasks with Vision transformers. Its underlying idea is simple: a portion of the input image is masked out and then reconstructed via a pre-text task. However, the wo…
Molecular dynamics (MD) has long been the de facto choice for simulating complex atomistic systems from first principles. Recently deep learning models become a popular way to accelerate MD. Notwithstanding, existing models depend on intermediate variables such as the potential energy or force field…
Procuring expressive molecular representations underpins AI-driven molecule design and scientific discovery. The research mainly focuses on atom-level homogeneous molecular graphs, ignoring the rich information in subgraphs or motifs. However, it has been widely accepted that substructures play a do…
The success of graph neural networks (GNNs) provokes the question about explainability: ``Which fraction of the input graph is the most determinant of the prediction?'' Particularly, parametric explainers prevail in existing approaches because of their more robust capability to decipher the black-bo…
We propose a novel formulation to use plane primitives in the direct sparse odometry formulation. Unlike existing SLAM works that introduce geometric error terms to account for planes, our method keeps the full error as purely photometric. The proposed system exploits the segmentation masks and plan
Robust pose graph optimization is essential for reliable pose estimation in Simultaneous Localization and Mapping (SLAM) system. Due to the nature of loop closures, even one spurious measurement could trick the SLAM estimator and severely distort the mapping results. Existing methods to avoid this p