Paper page - HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness
…if you push rlvr to grow both breadth and depth, i’d want to see how compute scales and whether there’s a sweet spot where extra trajectories stop paying off. This…
Search
Paper page - One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation
…recursively expands a single user click by (1) identifying reliable same-type locations through non-parametric gating of multi-scale encoder features , and (2) selecting the most spatially distant reliable point as…
Paper page - AdaState: Self-Evolving Anchors for Streaming Video Generation
…every generation step sees the same positional structure regardless of how far generation has progressed, and the state transition is identical at every chunk. Together, these properties introduce a recurrence into the…
Paper page - What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
…By constructing controlled tokenizer variants, we identify three key properties of a diffusion-friendly latent manifold : coherent spatial structure , local manifold continuity , and global manifold semantics . We find that these properties are…
Paper page - InterleaveThinker: Reinforcing Agentic Interleaved Generation
…Subsequently, we introduce a critic agent to evaluate the generator's outputs, identify samples that deviate from the planned instructions, and refine the instructions for regeneration. To implement this pipeline, we construct…
Paper page - EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions
…As a potential solution, we present a case study demonstrating that leveraging identified error patterns to preemptively detect and correct recognition errors, while requiring only minimal human intervention (e.g., routing 3…
Paper page - CIPER: A Unified Framework for Cross-view Image-retrieval and Pose-estimation
…Yurim Jeon , , Abstract CIPER is a unified cross-view geo-localization framework that simultaneously performs city-scale retrieval and precise 3-DoF pose estimation using a shared transformer encoder and two-way…
Paper page - Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
…We further identify that the conventional MTP training objectives ( cross-entropy or KL) are suboptimal in such settings, and therefore we propose a novel end-to-end TV loss that directly optimizes…
Paper page - When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
…This framework labels every turn along two independent axes (internal reasoning and visible output), yielding four operationally defined failure cells: robust alignment, alignment faking , overt jailbreak , and a distinct failure mode we…
Paper page - From Context to Skills: Can Language Models Learn from Context Skillfully?
…To prevent adversarial collapse caused by increasingly extreme task generation and over-specialized skill accumulation, we further introduce a Cross-time Replay mechanism that identifies the skill set achieving the best balance…