/// 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 Oct 2

In-Distribution Forcing for Long Video Generation at Test Time

Modern autoregressive (AR) video diffusion models excel at short-horizon video generation, yet generating long videos remains challenging due to drifting, where colors and textures...

21
Papers with Code paper Oct 2

Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps

Reinforcement learning for long-horizon agents relies on purely retrospective training signals: credit is assigned only after observing environmental consequences, leaving the agen...

21
Papers with Code paper Oct 2

Same Output, Different Gold: Measuring How Reference Choice Moves a Multilingual Benchmark Score

A benchmark score compares a system output against a reference, and methodological attention falls almost entirely on the first term. We measure the second. The retained annotation...

Benchmark
21
Papers with Code paper Oct 2

ProAR: Learning Prospective Reasoning with Autoregressive Video Models

Autoregressive (AR) video models excel at causal generation, but their reliance on next-chunk prediction confines them to a short-sighted, reactive paradigm. This limitation is par...

21
Papers with Code paper Oct 2

Multilingual GSM-Symbolic: What determines capability transfer across languages?

We understand little about how capabilities acquired in one language carry over to another, or what governs this transfer: evaluations rely on incomparable, saturation-prone datase...

21
Papers with Code paper Oct 2

Collective Bias Mitigation via Model Routing and Collaboration

Large language models (LLMs) are increasingly deployed in public health, finance, and governance, requiring both accuracy and societal value alignment. Despite recent advances, LLM...

21
Papers with Code paper Oct 2

HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning

Long-form thinking traces can substantially improve the multi-step reasoning performance of large language models (LLMs), but they introduce high inference-time overhead, with late...

21
Papers with Code paper Oct 2

Beyond the Parameter Monolith: Reconstructive Memories, Executable Skills, and Residual Assembly for Language Models

Language-model systems can separate contextual computation, persistent storage, and exact execution instead of updating all capabilities through one shared parameter system. We inv...

21
Papers with Code paper Oct 2

COSMI: COmpositional Synthesis of Multi-object Interactions

Generative models of human-object interaction are bounded by the data that exists: everyday activities involve several objects, but most captured datasets record one at a time, as ...

21
Papers with Code paper Oct 2

Learning Latent Protein Languages for Autoregressive Generation

Autoregressive transformers remain comparatively weak for protein sequence and structure generation. We study the role of target representation: amino acid tokens encode residue id...

21
Papers with Code paper Oct 2

Cross-Lingual Alignment for Decoder-Only Models using MoE Routers

Cross-lingual contrastive learning has been a core component of multilingual encoder training, but the ability to explicitly align representations is not possible in decoder-only L...

Safety/Alignment
21
Papers with Code paper Oct 2

Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale

A trainable input embedding table assigns each vocabulary item an independently adjustable vector. We investigate whether this token-specific parameterization is required for subst...

21
Papers with Code paper Oct 2

4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

We introduce 4DCodeBench, a benchmark for 4D inverse graphics through code generation, in which agents reconstruct dynamic scenes from video as executable graphics programs. To acc...

21
Papers with Code paper Oct 2

Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript

Full-duplex voice agents make many small, closed decisions, which current systems answer by slow autoregressive decoding. We propose DuplexJev, which feeds ASR-encoder hidden state...

LLM
21
Papers with Code paper Oct 2

DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation

Streaming video generation has benefited from distribution matching distillation (DMD), which matches the joint distribution of video frames to a video teacher's approximation of t...

21
Papers with Code paper Oct 2

Native Action-Prior Learning from Videos for World Action Models

World action models integrate future visual dynamics with robot action prediction, but their scalability remains limited by the need for action-annotated robot trajectories. Observ...

21
Papers with Code paper Oct 2

Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models

Masked diffusion language models (dLMs) offer a promising parallel alternative to autoregressive models for complex reasoning. However, they face a distinct credit-assignment chall...

21
Papers with Code paper Oct 2

FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution

LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prio...

LLM
21
Papers with Code paper Oct 2

Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards

Recent text-to-image generation models have achieved remarkable visual quality, but improving them through post-training remains challenging because no single reward signal capture...

Image Generation
21
Papers with Code paper Oct 2

Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing

Large language models (LLMs) increasingly serve as general-purpose interfaces to factual knowledge, but their parameters do not automatically reflect information that changes after...

21
Papers with Code paper Oct 2

PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation

World action models jointly learn to forecast world dynamics and predict robot actions, such that the learned internal world dynamics guide accurate actions. Existing approaches ty...

Robotics
21
Papers with Code paper Oct 2

What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document

Split learning lets a client train a language model on a server without sending its text. The client runs the first layers itself and sends the server only their output, a vector o...

OpenAI
21
Papers with Code paper Oct 2

CUAWright: A Minimal Unified Interface for Digital Agents

The prevailing approach to computer-use agents couples a model with a domain-specific harness: a browser or desktop environment equipped with human engineered tools that are fixed ...

21
Papers with Code paper Oct 2

DEPICT: Scoring Text-to-Image Alignment by Answer Agreement

Image-text alignment is a core problem in computer vision with applications in caption evaluation, hallucination detection, data curation, and the benchmarking of text-to-image (T2...

Image Generation Safety/Alignment
21
« Previous Page 65 of 292 (6986 items) Next »
AI Hub // AI Intelligence Platform // LIVE FEED // Impressum // Datenschutz © 2026
0 new articles available