Tag
Proposes TRACER, a framework that integrates severity-grounded knowledge graphs and retrieval-augmented generation for trajectory-aware clinical risk prediction, achieving large gains in mortality and readmission prediction on MIMIC-III and MIMIC-IV datasets.
Introduces SeqGeo-VL dataset and TrajLoc framework for trajectory-aware cross-view geo-localization using sequential observations (video clips or route descriptions), achieving substantial gains over state-of-the-art methods.
TACG is a training-free decoder for diffusion language models that uses trajectory-aware signals to decide when to commit tokens, improving accuracy and efficiency on code and math benchmarks.
Introduces SciTrace, a framework that integrates safety reasoning into every stage of scientific agent pipelines using a Safety-Intrinsic Reasoning Loop and a Compositional Tool-Chain Verifier, achieving state-of-the-art safety while preserving output quality.
TRACE is a trajectory-aware LLM agent for molecular lead optimization that uses sequential decision-making over molecular optimization tools, achieving improved ADMET properties while preserving molecular similarity.
Proposes Manifold-Guided Attention Steering (MAGS), a trajectory-aware inference-time intervention that corrects reasoning errors in LLMs by projecting attention outputs back to a learned correctness manifold when deviation exceeds a threshold, outperforming static steering methods across math, code, and molecular benchmarks.
This paper introduces TABOM, a self-distilled trajectory-based post-training framework for Diffusion Language Models that aligns training with inference trajectories using Boltzmann modeling to mitigate the training-inference discrepancy and reduce catastrophic forgetting.