TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models
Tabular foundation models achieve strong zero-shot accuracy on structured data by pretraining on synthetic tables, but they ignore the column names, task descriptions, and auxiliar...
Papers
AIM: Agentic Idea Management for Automated Research
Frontier LLMs are increasingly used to automate scientific research through iterative search. We distinguish idea-driven search from solution-driven search and identify three core ...
Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning
TTS systems with autoregressive semantic modeling have demonstrated strong zero-shot voice cloning performance and rich expressive variation, but their sequential decoding incurs s...
Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards
Group-relative methods for reinforcement learning with verifiable rewards (RLVR) learn from differences in rollout outcomes. Independently sampling complete trajectories is costly ...
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation
On-policy distillation (OPD) reduces train-test state mismatch by training a student on its own generated trajectories, but weak students may visit teacher-misaligned prefixes wher...
Improved Distributional Diffusion Models
Distributional Diffusion Models (DDMs) replace the standard mean-prediction denoiser with a distributional denoiser trained via a scoring rule objective, learning a stochastic appr...
Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics
On-policy distillation (OPD) trains multi-turn language agents with dense teacher supervision on student-generated responses. However, standard think-then-act rollouts require leng...
PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning
Language-model agents are usually trained by reinforcement learning from one reward per episode, and privileged self-distillation enriches it by letting the same policy, given a sk...
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?
Training a model to generate visual content can encourage it to learn rich perceptual capabilities related to geometry, spatial relationships, and objectness; yet, its benefits for...
HiRAE: Hierarchical Representation Autoencoding with Residual Budgets
Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. Meanwhile, intermediate encoder ...
Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies
GPT-6 Astra exhibits a remarkable ability to generate numerical robot actions, extending its role beyond high-level planning. To assess Astra's capabilities as general-purpose embo...
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
World action models (WAMs) predict the future alongside actions during training. Due to the heavy computation cost of video denoising, whether the future must still be generated du...
Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR
Reinforcement Learning with Verifiable Rewards (RLVR) methods such as GRPO rely on successful self-generated trajectories, but finite rollout budgets can produce all-fail groups wi...
Think Before You Score: Thinking Reward Model for Visual Generation
Visual reward models are essential for evaluating and improving visual generation models, yet existing approaches typically map task conditions and candidate outputs directly to sc...
It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them
Vision-language models (VLMs) are increasingly used in place of human annotators, making it important that substitutability tests reflect the model rather than incidental evaluatio...
Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym
Proactive LLM agents can turn idle compute into useful support before users ask. Yet even correct work can misread user context, impose review costs, or undermine trust. This work ...
RLE-Bench: A Qualifying Exam for Coding Agents as Robot Learning Engineers
Coding agents are beginning to move beyond purely digital tasks to tackle physical-world challenges, particularly in robotics. Existing robotics benchmarks, however, primarily focu...
In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks
We study robotic in-context learning (ICL), an emerging paradigm that enables robots to infer and execute tasks from visual demonstrations. Despite its growing promise, the problem...
Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models
Audio-visual large language models (AVLLMs) have made remarkable progress in multimodal understanding and reasoning through interactions among visual, auditory, and linguistic info...
What Makes Recurrence Effective in Looped Language Models?
Looped language models (LoopLMs) increase computational depth through parameter sharing, offering a path to scale inference computation without adding parameters. However, it remai...
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation
Backdoor attacks can be implanted in Large Language Models (LLMs) during training, causing unwanted behaviour when a trigger appears in the input. Existing backdoor defences for LL...
MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation
Vision-language-action (VLA) models have advanced robotic manipulation, but their zero-shot generalization in new tasks and environments remains limited, and their reliance on spec...
Beyond Prompt Count: How Data Shapes Transfer in On-Policy Distillation
On-policy distillation (OPD) trains students using teacher feedback on their own sampled responses, yet how prompt choice shapes transfer across teacher-student pairs remains poorl...
Inducing Process Supervision from Outcome-Only Reinforcement Learning
Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time reasoning. However, training strong PRMs r...