Downstream Reasoning

Ask about this topic

Recent momentum

-76%

4 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

1 new paper

A weekly snapshot of new work published in Downstream Reasoning.

Period ending 2026-09-07

6 new papers

A weekly snapshot of new work published in Downstream Reasoning.

76 papers

Latest in Downstream Reasoning

Open your feed →
CardsList

  1. Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack

    Sep 8, 2026Sohir Maskey, Philipp Scholl, Jonas Knupp +2Model CheckpointsModel Pretraining

  2. HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

    Sep 1, 2026Yuhao Wu, Jingyuan Zhang, Jiajun Shi +16Agent HarnessDownstream Reasoning

  3. LaMoC: Loss-Aware Modular Compression for LLMs

    Aug 31, 2026Mohanad Odema, Jacob SongLarge Language Model CompressionModel and Context Compression

  4. Learning Representations through Token Prediction: Geometry, Approximation, and Downstream Guarantees

    Aug 30, 2026Shulei WangNext-Token PredictionRepresentation Learning

  5. Linearized 2-Simplicial Attention

    Aug 10, 2026Aritra Das, Dhruman Gupta, Debayan GuptaEfficient Long-Context InferenceDownstream Reasoning

  6. Backward Compatibility in Tree-Based Explanations and Enhanced CART Algorithm

    Aug 9, 2026Hirofumi SuzukiDecision TreesExplanations

  7. TSDS-Toolbox: A Toolbox for Measuring Time-Series Dataset Similarity

    Aug 8, 2026Yen-Ku Liu, Hongjie Chen, Ryan A. Rossi +1Time SeriesSemantic Similarity Metrics

  8. TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories

    Aug 6, 2026Yunjia Qi, Zehua Yin, Xintong Shi +10Step-Level Failure AttributionLong-Horizon Agents

  9. CASCADE: An Agentic Regulatory Network Framework for Patient-Data-Validated Downstream Perturbation Prediction

    Aug 5, 2026Jose A. BirdThe Cancer Genome Atlas DatasetsTranscriptomics

  10. ContextWeave: A Real-World Workflow Benchmark

    Aug 5, 2026Bo Wang, Yuqian Yao, Enxi Wang +25Workflow Automation and OptimizationMemoryagentbench

  11. Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving

    Aug 4, 2026Xiang Li, Pengcheng Wang, Huazheng Wang +1Low-Rank AdaptersGraphics Processing Unit Memory

  12. Decoupling semantics from vision: A framework for faithful visual-text compression evaluation

    Aug 3, 2026Yonghan Gao, Zehong Chen, Lijian Xu +3Token CompressionDeepseek-Ocr

  13. β-OPSD: Deriving with Policy Optimization, Training with Self-Distillation

    Jul 30, 2026Jiawei Xu, Minghui Liu, Juzheng Zhang +2Unsupervised On-Policy Self-DistillationSelf-Distillation

  14. WikiLoop: Jointly Learning to Build and Navigate Agent-Native Wikis with Downstream Feedback

    Jul 29, 2026Haoliang Ming, Feifei Li, Wenhui QueWikipediaDownstream Reasoning

  15. DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data

    Jul 27, 2026Zhen Huang, Yikun Wang, Shijie Xia +1Data-CurationModel Pretraining

  16. Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects

    Jul 27, 2026Phu Gia Hoang, Anwoy Chatterjee, Tanmoy Chakraborty +2Improving Sparse AutoencodersSparse Autoencoders

  17. LabRobFail: A Benchmark for Robotic Failure Analysis in Chemical Self-driving Laboratory

    Jul 26, 2026Haobo Wang, Baoli Sun, Anqi Zou +8Downstream ReasoningVideo Large Language Models

  18. PathSelect: Sequential Token Selection for Whole Slide Pathology

    Jul 26, 2026Jingzhi Chen, Landi He, Zehong Chen +2Visual Token PruningWireless Foundation Models

  19. Source-Prior-Driven Selective Adaptation for Efficient Diffusion Model Finetuning

    Jul 23, 2026Yi Xiong, Yuan-Yuan Cheng, Xiao-Ming FuDiffusion ModelsParameter-Efficient Adaptation

  20. Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

    Jul 22, 2026Kailin Jiang, Lei Liu, Jian Xi +7Query-Document PairsRelevance

  21. LLM Detection as an Intervention: Downstream Impact under Strategic User Behavior

    Jul 21, 2026Meena Jagadeesan, Tatsunori Hashimoto, Jon KleinbergSide EffectsDownstream Reasoning

  22. A multiverse-consensus pipeline for reproducible feature selection in untargeted LC-MS metabolomics

    Jul 19, 2026Mohammed Saeed Al-Huraibi, Ihsan Yozgat, Ahmet KaplanMetabolicFeature Selection

  23. Scalable and Trustworthy Earth Observation Foundation Models

    Jul 8, 2026Syed Usama Imtiaz, Mitra Nasr Azadani, Nasrin AlamdariGeospatial Foundation ModelsCloud-Aware Earth Observation Sequences

  24. RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs

    Jul 6, 2026Damian Hodel, Jevin West, Aylin CaliskanLarge Language Model EvaluationEvaluation Metrics

  25. Causal ASCEND: Scalable Two-tier Causal Discovery on High Dimensional Multi-omics Data

    Jul 5, 2026Stephen Asiedu, David WatsonCausal DiscoveryRegulatory Networks

  26. Joint distribution of upstream runoff governs downstream river-discharge prediction uncertainty in distributed ML models

    Jul 3, 2026Karan Ruparell, Tristan Hascoet, Takemasa Miyoshi +4Fundamental Hydrological PrinciplesAccurate Flood Prediction

  27. Predicting Closed-Loop Performance of Latent World Models: Offline Checkpoint Selection for MPC and Model-Based RL Under Non-Markovian Rewards in LunarLander

    Jul 2, 2026Nikolai SmolyanskiyLatent World ModelsClosed-Loop Performance

  28. MemSyco-Bench: Benchmarking Sycophancy in Agent Memory

    Jul 1, 2026Zhishang Xiang, Zerui Chen, Yunbo Tang +5Agent MemorySycophancy

  29. Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding

    Jun 29, 2026Tianyu Wang, Gourav Rattihalli, Aditya Dhakal +4Dynamic Sparse AttentionEfficient Long-Context Inference

  30. Improved Multi-Dimensional Forecasting for Swap Regret

    Jun 28, 2026Joey Rivkin, Ramiro N. Deo-Campo Vuong, Robert Kleinberg +3RegretTime Series Forecasting

  31. Pseudo-Text-Conditioned 3D Grounding DINO for Organ Localization in Abdominal CT

    Jun 25, 2026Siqi Chen, Han Gong, Keyi Hou +33D Visual GroundingLocalization

  32. Refusal Lives Downstream of Persona in Chat Models

    Jun 24, 2026Viola Zhong, Qirui LiRefusalsPersonas

  33. SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks

    Jun 23, 2026Zhewen He, Junyi Hu, Haomian Huang +3Sign Language TranslationData Augmentation

  34. AwakeForest: An Interactive Geospatial Platform for Large-Scale Forest Imagery

    Jun 22, 2026Suraj Prasai, Kangning Cui, Rongkun Zhu +5ForestsComputer Vision

  35. Is Agent Code Less Maintainable Than Human Code?

    Jun 19, 2026Shaswat Patel, Betty Li Hou, Arun Purohit +4Coding AgentsHumanity

  36. Decision-Focused Learning: When and Why Traditional Prediction Models Fail

    Jun 19, 2026Mo LiuPredictive UncertaintySequential Decision Making

  37. Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment

    Jun 17, 2026Miloš Nikolić, Ali Hadi Zadeh, Enrique Torres Sanchez +1Large Language Model QuantizationKullback-Leibler Divergence

  38. How Far Can Machine Translation Quality Take You? Extrinsic Discourse Evaluation in Goal-Oriented Setups

    Jun 15, 2026Wafaa Mohammed, Kata Naszadi, Vlad NiculaeMachine Translation QualityMachine Translation

  39. Models Take Notes at Prefill: KV Cache Can Be Editable and Composable

    Jun 14, 2026Bojie LiCachePrefill

  40. TAKE: Trajectory-Aware Knowledge Estimation for Text Dataset Distillation

    Jun 13, 2026Tri-Nhan Vo, Dang Nguyen, Sunil GuptaNatural Language DatasetsDownstream Reasoning

  41. How do Self-Supervised Remote Sensing Vision Models Transfer to Downstream Tasks?

    Jun 11, 2026Julia Romero, Qin Lv, Morteza KarimzadehGeospatial Foundation ModelsRecent Vision Foundation Models

  42. A Universal Dense Football Event Representation Based on TabTransformer

    Jun 8, 2026Weiran Yang, Daniel Memmert, Maximilian Klemp-WeinsSports AnalyticsSpatio-Temporal Transformers

  43. SWE-Explore: Benchmarking How Coding Agents Explore Repositories

    Jun 5, 2026Shaoqiu Zhang, Yuhang Wang, Jialiang Liang +8Repository-Level Code UnderstandingCoding Agents

  44. From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents

    Jun 4, 2026Yuhao Sun, Jiacheng Zhang, Shaanan Cohney +3Streaming GuardrailsGuardrail

  45. QueryAgent-R1: Bridging Query Generation and Product Retrieval for E-Commerce Query Recommendation

    Jun 4, 2026Dike Sun, Zheng Zou, Jingtong Zang +3ProductsMulti-Hop Retrieval

  46. Diff2SP: Diffusion Models for Correlated Scenario Generation in Stochastic Programming

    Jun 4, 2026Haixiang Sun, Andrew LiuScenario GenerationStochastic Optimization

  47. Tailoring Strictly Proper Scoring Rules for Downstream Tasks: An Application to Causal Inference

    Jun 2, 2026Roman Plaud, Alexandre Perez-Lebel, Antoine Saillenfest +4Causal InferencesPropensity

  48. Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults

    May 30, 2026Rana Muhammad UsmanLarge Language Model AgentsDownstream Reasoning

  49. Conformal Certification of Reasoning Trace Prefixes

    May 28, 2026Matt Y. Cheung, Ashok Veeraraghavan, Hanjie Chen +1Reasoning TracesProbabilistic Verification

  50. Routing-Aligned Fine-Tuning for Multilingual Downstream Tasks in Mixture-of-Experts Models

    May 27, 2026Guanzhi Deng, Kuan Wu, Haibo Wang +3Mixture-Of-Expert Language ModelsLarge Language Model Routing

  51. SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling

    May 27, 2026Quanen Sun, Changxin Tian, Ke Shi +6Downstream Fine-TuningOut-Of-Distribution

  52. Simulating Human Memory with Language Models

    May 25, 2026Qihan Wang, Nicholas Tomlin, Michael Hu +2Human MemoryDownstream Reasoning

  53. ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis

    May 24, 2026Guohong Liu, Jialei Ye, Pengzhi Gao +4Graphical User Interface AgentsCoding Agents

  54. State commitment learning: training language models to distinguish computation from memory

    May 22, 2026Fei Ding, Yongkang Zhang, Runhao Liu +3Protein Language ModelPersistent State

  55. Most Transformer Modifications Still Do Not Transfer at 1-3B: A 2020-2026 Update to Narang et al. (2021) with Downstream Evaluation and a Noise Floor

    May 20, 2026Yang Zhao, Jiahao Lu, Bin Huang +2Transformer VariantDownstream Reasoning

  56. What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems

    May 19, 2026Yong Jin Chun, Iftekhar AhmedError PropagationDownstream Reasoning

  57. FLUXtrapolation: A benchmark on extrapolating ecosystem fluxes

    May 19, 2026Anya Fries, Jacob A Nelson, Martin Jung +2ExtrapolationEcosystems

  58. SAME: A Semantically-Aligned Music Autoencoder

    May 18, 2026Julian D. Parker, Zach Evans, CJ Carr +4AutoencoderNeural Audio Codecs

  59. Forecasting Downstream Performance of LLMs With Proxy Metrics

    May 18, 2026Arkil Patel, Siva Reddy, Marius Mosbach +1Predictive PerformanceDownstream Reasoning

  60. Trustworthy Multi-Agent Systems: Mitigating Semantic Drift with the Argent Signaling Protocol

    May 14, 2026Anantha SharmaMulti-Agent Large Language Model SystemsRetrying