The paper introduces ProtStructQA, an executable benchmark that tests protein structural reasoning by requiring language models to generate measurable 3D coordinates, revealing a capability-dependent…

This paper develops a parameterized algorithm for the NP-complete Tree Containment problem, showing it can be solved efficiently based on a structural parameter called scanwidth.

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…

MOSAIC is a multi-objective framework that efficiently allocates a fixed supervised fine-tuning budget by turning failure profiles into actionable data mixtures, significantly improving model alignmen…

The paper analyzes the structured CVP distance on the log-unit lattice of cyclotomic fields, significantly reducing the conjectured CDPR factor for the ML-KEM cryptosystem from exponential to sub-poly…

AgentPLM introduces a novel framework that enhances protein language models by integrating external biophysical tools and a specialized policy optimization, enabling active, reasoning-based protein se…

The paper introduces RAG-Pref, a novel, training-free Retrieval Augmented Generation (RAG) method for preference alignment that significantly improves LLM refusal guardrails against agentic attacks wi…

The paper introduces PROBE, an optimization framework that guides LLM agents in structure-based drug design by performing controlled 'probe edits' to assess how molecular changes affect both binding a…

This paper presents an algorithmic framework for exhaustively generating and tabulating knot and link diagrams on the thickened torus.

SERSEM introduces a selective entropy-weighted scoring framework to significantly improve Membership Inference Attacks (MIAs) against code LLMs by focusing on human-centric coding anomalies rather tha…

The paper establishes information-theoretic lower bounds for stochastic optimization using low-bit gradients by reducing the problem to compressed Gaussian mean estimation, yielding sharp bounds on co…

The paper introduces Semantic Triplet Restoration (STR), a novel protocol that converts complex table structures into atomic semantic triplets, improving table question answering by providing explicit…

The paper evaluates LLM reasoning on Boolean satisfiability (SAT) problems, concluding that conventional metrics are misleading and proposing a paired-formula protocol with Accurate Differentiation Ra…

The paper introduces SGAP-PPIS, a structure-guided adaptive propagation model that improves protein-protein interaction site prediction by allowing information diffusion to adapt based on a residue's…

The paper identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…

The paper proposes using Maximum Independent Set (MIS) algorithms on similarity graphs to select a maximally diverse and non-redundant subset of prompts for LLM benchmarking, achieving consistent rank…

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…

FuzzPilot is a controller for AFL++ that validates candidate mutation recipes by running short micro-campaigns, demonstrating a mechanism to manage fuzzing plateaus, though initial results on a satura…