/// 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 28

Does Native 3D Texture Generation Necessarily Require 3D Assets for Training?

Native 3D texture generation synthesizes colors directly in 3D space for a given geometry, conditioned on multi-view reference images. It is generally believed that training such m...

21
Papers with Code paper Sep 28

Imprint Reader: From Weight-Update Readout to Behavioral Intervention

As language models take a growing role in AI development, a natural aspiration is for them to reflect on their own learning process, as humans do, and use that reflection to improv...

21
Papers with Code paper Sep 28

ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport

Multi-vector retrievers built on vision-language models lead visual document retrieval (VDR), but they run a multi-billion-parameter query encoder on every search. Distilling this ...

21
Papers with Code paper Sep 28

How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining

Most modern multimodal large language models (MLLMs) build on a pretrained visual encoder that provides a strong visual prior. Encoder-free MLLMs instead learn visual representatio...

Multimodal
21
Papers with Code paper Sep 28

When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety

Reliable AI safeguards require both control mechanisms that reduce unsafe behavior and monitoring mechanisms that detect safety risks during model interactions. Established behavio...

LLM
21
Papers with Code paper Sep 28

InfiniHand: Streaming World-Space Hand Motion Estimation from Egocentric Video

World-space hand motion estimation from egocentric video requires recovering 3D articulated hand geometry while tracking camera egomotion. Existing approaches heavily rely on casca...

21
Papers with Code paper Sep 28

QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models

Video world models achieve long-range temporal consistency by storing KV cache during generation, but the growing cache makes KV cache memory a major deployment bottleneck, which m...

21
Papers with Code paper Sep 28

GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space

Novel view synthesis from sparse images must reconcile faithful reconstruction of observed regions with plausible completion of unseen content, while maintaining world consistency ...

21
Papers with Code paper Sep 28

Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models

Long visual token sequences often account for a substantial fraction of the computational overhead in multimodal large language models~(MLLMs). Existing approaches reduce this cost...

Multimodal
21
Papers with Code paper Sep 28

Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression

Chunked KV-cache compression reduces the memory and attention costs of long-context inference by compressing windows of consecutive tokens into fewer cache entries at a fixed strid...

21
Papers with Code paper Sep 28

ControlScope: Workflow Revision and Reliability in LLM Agents

How much of a running workflow should a language model agent revise? ControlScope compares continuing generated code, editing the next tool call's data arguments, and replacing the...

LLM
21
Papers with Code paper Sep 28

Org-Agent: Beyond Personal Assistants Towards Organizational Agents

Language model agents serving organizations must coordinate requests from multiple users while using knowledge distributed across their interactions. We identify two complementary ...

21
Papers with Code paper Sep 28

AutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?

Recent gains in language model capability have come more from data than from architecture. Frontier labs and data companies produce verifiable agentic tasks, which supervised finet...

21
Papers with Code paper Sep 28

Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation

RLVR provides reliable trajectory-level credit, while OPSD offers dense supervision for token-level credit. This exposes a fundamental coupling when updating step-level credit dire...

21
Papers with Code paper Sep 28

Beyond Selection: Token Parameterization for Extreme Visual Token Compression

Visual-token compression is effective for improving the efficiency of vision-language models, but under extreme compression budgets, token pruning can break visual grounding while ...

21
Papers with Code paper Sep 28

Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation

Long-horizon camera-controlled video generation requires recovering previously observed content from an ever-growing visual history. Existing approaches either search historical co...

21
Papers with Code paper Sep 28

LEGO-Anything: Coding Agents for 3D Scene Reconstruction

A 3D scene reconstructed from a single image is most useful when represented not as a rendering or a fixed 3D output, but as an explicit scene program whose execution yields a scen...

OpenAI
21
Papers with Code paper Sep 28

SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models

Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pruning reduces this cost, but...

Multimodal
21
Papers with Code paper Sep 28

PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation

Recent vision-language models (VLMs) have advanced vision-and-language navigation (VLN), enabling models to predict navigation actions from visual observations and language instruc...

Multimodal
21
Papers with Code paper Sep 28

ROSS: Relearning from Self-Generated Rollouts through Selective Supervision

Large language model post-training generates self-generated rollouts through reinforcement learning and on-policy distillation, yet this experience is often treated as stale once t...

21
Papers with Code paper Sep 28

Learning What to Recall: Adaptive Multi-Cue Episodic Memory for World Models

World models predict future observations from current experience and actions, yet prediction can depend on observations seen far in the past. Episodic memory preserves past observa...

21
Papers with Code paper Sep 28

In-Context Learning for Robots: Methods and Applications

General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL) for robots supports this pro...

21
Papers with Code paper Sep 28

AutoRef: Harness Optimization for Agentic Multi-Reference Image Generation

Recent image generation models can take multiple reference images as input and combine them into a new image. However, multi-reference image generation remains challenging: models ...

Agents
21
Papers with Code paper Sep 28

See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs

Safety-aligned LLMs can exhibit emergent misalignment (EM): narrow domain adaptation unexpectedly triggers catastrophic safety failures across unrelated domains. Prior static analy...

21
« Previous Page 82 of 292 (6993 items) Next »
AI Hub // AI Intelligence Platform // LIVE FEED // Impressum // Datenschutz © 2026
0 new articles available