Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action Saurabh Pujar, Ira Ceka, Irene L Manotas, Gail Kaiser, Baishakhi Ray, Shyam Ramji Action editor: Quanming Yao https://openreview.net/forum?id=zZa3u6LKwO #coding #code #tool

Tabular Learning Revisited: An Empirical Study of Tabular Classification Guri Zabërgja, Arlind Kadra, Christian Frey, Josif Grabocka Action editor: Philip Chan https://openreview.net/forum?id=I8BIGp4XOb #tabular #benchmark #datasets

Time-Aware Prior Fitted Networks for Zero-Shot Forecasting with Exogenous Variables Andres Potapczynski, Ravi Kiran Selvam, Tatiana Konstantinova et al. Action editor: Andreas Lehrmann https://openreview.net/forum?id=nJARpxp3cF #forecasting #forecasts #forecasters

Reference-Guided Identity Preserving Face Restoration Mo Zhou, Keren Ye, Viraj Shah et al. Action editor: Søren Hauberg https://openreview.net/forum?id=g9YzUDnUUS #restoration #faces #preserving

Robust Cross-Domain Alignment Anish Chakrabarty, ARKAPRABHA BASU, Swagatam Das Action editor: Bamdev Mishra https://openreview.net/forum?id=0mchjaZZi4 #robust #robustness #robustify

LLM-Guider: A Language-Guided Discovery of Symbolic Pruning Metrics for Post-Training Sparsity in... Jędrzej Hasiura, Prashant Shivaram Bhat, Elahe Arani, Bahram Zonooz Action editor: Zhengzhang Chen https://openreview.net/forum?id=SlVQxEiYnY #pruning #formulas #symbolic

CADO: From Imitation to Cost Minimization for Heatmap-based Solvers in Combinatorial Optimization Hyungseok Song, Deunsol Yoon, Kanghoon Lee, Han-Seul Jeong, Soonyoung Lee, Woohyung Lim Action editor: Aleksandra Faust https://openreview.net/forum?id=fvxx5FOED6 #optimize #reinforcement

Numerical Analysis of HiPPO-LegS ODE for Deep State Space Models Jaesung R. Park, Jaewook J. Suh, Youngjoon Hong, Ernest K. Ryu Action editor: Pierre Ablin https://openreview.net/forum?id=83dhVASBPn #discretization #discretizations #odes

A Survey of Flow Matching in Reinforcement Learning Nabuat Zaman Nahim, Fairoz Nower Khan, Peizhong Ju Action editor: Shangtong Zhang https://openreview.net/forum?id=P6e5IC4gPe #flow #reinforcement #learned

Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretab... Harshvardhan Saini, Yiming Tang, Dianbo Liu Action editor: Xingchen Wan https://openreview.net/forum?id=dcmHPxgo4c #prompts #prompt #ai

New #Survey Certification: A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents Wei-Chieh Huang, Weizhi Zhang, Yueqing Liang et al. https://openreview.net/forum?id=XycbogUAeJ #memory #agent #agents

RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deployable An... Anushiya Arunan, Xin Li, Yan Qin, U-Xuan Tan, VUONG NHU KHUE, Xiaoli Li, Chau Yuen Action editor: David Fouhey https://openreview.net/forum?id=skrA9UYNIZ #robustness #robustmad

NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning Michael M. Jerge, David Evans Action editor: Ilia Sucholutsky https://openreview.net/forum?id=5aatZPiCv8 #counterfactual #reasoning #inference

Maximizing Confidence Alone Improves Reasoning Mihir Prabhudesai, Lili Chen, Alex Ippoliti, Katerina Fragkiadaki, Hao Liu, Deepak Pathak Action editor: Peilin Zhao https://openreview.net/forum?id=gInznr8EsQ #reward #reinforcement #answers

Multitask Transformer Models for Demographic and Industry Profiling on Long-Form Blog Texts Bahor Eshmirzayeva, Shirali Kadyrov Action editor: Cedric Archambeau https://openreview.net/forum?id=WtFwcCvt9i #multitask #blog #profiling

Differentially Private XGBoost Revisited: Is Random Decision Trees Really Better than Greedy Ones? Erchi Wang, Arinbjörn Kolbeinsson, Luca Foschini, Yu-Xiang Wang Action editor: Antti Honkela https://openreview.net/forum?id=9fRDcavm3J #privacy #xgboost #boosting

Beyond Subtokens: A Rich Character Embedding for Low-Resource and Morphologically Complex Languages Felix Schneider, Maria Gogolev, Sven Sickert, Joachim Denzler Action editor: Adín Ramírez Rivera https://openreview.net/forum?id=4n4db5qmXZ #tokenization #word2vec #subtokens

New #J2C Certification: PAC-Bayesian Meta-Learning for Few-Shot Identification of Linear Dynamical Systems Chenfeng Huang, George Michailidis https://openreview.net/forum?id=CiGFpSLzFv #learns #learn #learned

On The Scalability Of Forward Gradients, Evolution Strategies, And Control Variates Jake Levi, Seth Nabarro, Mark van der Wilk Action editor: Yutian Chen https://openreview.net/forum?id=s6g8yZimHE #backpropagation #gradients #gradient

New #Expert Certification: NeMoS: Nearest Neighbors Bandit meets Active Learning for Online Model Selection Jules Damidaux, Basile Lewandowski, Farzan Farnia, Lydia Chen https://openreview.net/forum?id=CSjewjplO1 #bandit #bandits #reward

Reduced-Rank Outcome Compression for Causal Policy Optimization Ezinne Nwankwo, Michael I. Jordan, Angela Zhou Action editor: Bryon Aragam https://openreview.net/forum?id=WQhOaY4yPC #outcomes #interventions #policymakers

New #Survey Certification: Wiring the ‘Why’: A Unified Taxonomy and Survey of Abductive Reasoning in LLMs Moein Salimi, Shaygan Adim, Danial Parnian et al. https://openreview.net/forum?id=oeVkugH0WB #abductive #abduction #reasoning

O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering Jianbiao Mei, Tao Hu, Daocheng Fu et al. Action editor: Sylvain Le Corff https://openreview.net/forum?id=rbIKFKFEeU #answering #reinforcement #reward

New #J2C Certification: Provably Safe Generative Sampling with Constricting Barrier Functions Darshan Gadginmath, Ahmed Allibhoy, Fabio Pasqualetti https://openreview.net/forum?id=iZi471b4Pf #barrier #generative #flow

Temporal Variational Implicit Neural Representations Batuhan Koyuncu, Rachael DeVries, Ole Winther, Isabel Valera Action editor: Michael Zhang https://openreview.net/forum?id=1CGfvw4ySe #imputation #forecasting #latent

Data Selection Through Iterative Self-Filtering for Vision-Language Settings Andrei Liviu Nicolicioiu, Sarvjeet Singh Ghotra, Morgane M Moss, Aaron Courville Action editor: Vincent Fortuin https://openreview.net/forum?id=F09NfCXuCe #filtering #dataset #datasets

Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipel... Sadman Kabir Soumik Action editor: Colin Raffel https://openreview.net/forum?id=QF4lAmG4zc #bias #biases #judges

Adaptive Budget Allocation for Orthogonal Subspace Adapter Tuning in LLMs Continual Learning Zhiyi Wan, Wanrou Du, Yijia Chi, Liang Li, Miao Pan, Xiaoqi Qin Action editor: Martin Mundt https://openreview.net/forum?id=LNGDlLOdex #forgetting #adaptive #allocated

TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning Zhangchen Xu, Yuetai Li, Fengqing Jiang et al. Action editor: Masashi Sugiyama https://openreview.net/forum?id=HMGsqApBM3 #negatives #rl #reinforcement

Firewalls to Secure Dynamic LLM Agentic Networks Sahar Abdelnabi, Amr Gomaa, Eugene Bagdasarian, Per Ola Kristensson, Reza Shokri Action editor: Alessandro De Palma https://openreview.net/forum?id=w02FW1dMoY #firewalls #firewall #security