/// AI HUB
Dashboard News Models Tools Papers Repos Videos Companies Trending
Login

Research Papers

Latest AI/ML research from ArXiv and Papers with Code

Latest Trending
Papers with Code paper Sep 18

Calibrating Teacher--Student Discrepancy for On-Policy Distillation

On-policy distillation (OPD) improves reasoning models by learning the token-level discrepancy between a stronger teacher and an on-policy student. However, this discrepancy does n...

21
Papers with Code paper Sep 18

IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts

Mixture-of-Experts (MoE) scales capacity, but existing designs cannot set three quantities independently. For a single token, participation is how many experts contribute knowledge...

21
Papers with Code paper Sep 17

DeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot Manipulation

Creating deformable assets for robot manipulation requires jointly specifying their geometry, appearance, and physical properties. This is especially challenging for deformable obj...

Robotics
21
Papers with Code paper Sep 17

When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation

Large language models (LLMs) increasingly participate in scientific evaluation, both as automated reviewers and as assistants to human reviewers. As model-generated reviews enter p...

21
Papers with Code paper Sep 17

TeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection

Telecom fraud scripts evolve rapidly and are often designed to resemble routine service conversations, creating two key requirements for audio-based telecom-fraud evaluation. First...

Benchmark
21
Papers with Code paper Sep 17

Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models

Large Language Models (LLMs) are increasingly deployed in applications that must weigh clashing moral values, yet even strong models exhibit hidden biases and brittle instruction-f...

OpenAI Safety/Alignment
21
Papers with Code paper Sep 17

Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network

Text-guided image editing must introduce the requested changes while preserving unrelated source content. Diffusion-based editors rely on spatial controls whose inaccuracies can le...

21
Papers with Code paper Sep 17

VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control

Spatial intelligence requires more than describing object locations. Under incomplete observation, models must identify and acquire missing evidence, interpret it in a common spati...

21
Papers with Code paper Sep 17

Region-Level Policy Optimization for Fine-grained MLLM Perception

Fine-grained visual perception in MLLMs is commonly improved by raising the resolution, but the added visual tokens inflate vision-encoding and language-model prefilling costs. We ...

21
Papers with Code paper Sep 17

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands from isolated predictions into long trajectories of reasoning,...

OpenAI
21
Papers with Code paper Sep 17

An Empirical Study of Harness Design for Coding Agents

Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses...

21
Papers with Code paper Sep 17

Paint-Anything: Unified Any-Color Control for Image Generation and Editing

Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored ...

21
Papers with Code paper Sep 17

FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations

Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence. Most feed-forward methods infer ...

21
Papers with Code paper Sep 17

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

We study length inflation in on-policy distillation (OPD), where student responses can become excessively long and even exhaust the generation budget. We identify termination-token...

Google
21
Papers with Code paper Sep 17

WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing

Document parsing converts document images into structured content and requires reliable performance across diverse layouts and acquisition conditions. Yet training corpora are bias...

21
Papers with Code paper Sep 17

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-le...

Agents
21
Papers with Code paper Sep 17

When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models

Large Reasoning Models (LRMs) achieve strong performance on complex tasks but exhibit systematic inefficiency: they often overthink easy problems and underthink hard ones. Existing...

21
Papers with Code paper Sep 17

What Does Privileged Information Add to On-Policy Self-Distillation?

On-policy self-distillation (OPSD) lets a language model learn from a frozen copy of itself that sees an answer or a worked solution. Giving the teacher this extra information seem...

21
Papers with Code paper Sep 17

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation...

21
Papers with Code paper Sep 17

UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation

Multi-modal image generation, particularly subject-driven customization, has garnered growing attention in recent years. Despite the rapid advancement of generative models, their e...

Safety/Alignment
21
Papers with Code paper Sep 17

Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation

Video diffusion models repeatedly process long spatiotemporal token sequences during denoising, making attention a major computational bottleneck. Linear attention offers an appeal...

21
Papers with Code paper Sep 17

JEPA-Anything: Learning Predictive Models across Different Worlds

World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction. Yet predictive models remain domain-specific: can a common learning...

21
Papers with Code paper Sep 17

Learning Foresight without Explicit Trajectories for 3D Diffusion Policies

3D diffusion policies are strong at generating geometrically grounded actions from current observations, but successful manipulation requires not only knowing what motion is feasib...

21
Papers with Code paper Sep 17

VākQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering

Question answering has advanced rapidly with large language models, but predominantly for high-resource languages, in both text and spoken settings. Spoken question answering (SQA)...

Google Benchmark
21
« Previous Page 96 of 294 (7047 items) Next »
AI Hub // AI Intelligence Platform // LIVE FEED // Impressum // Datenschutz © 2026
0 new articles available