Hugging Face Daily Papers

95 posts · huggingface.co

HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness arxiv.org
HarnessVLN introduces a zero‑shot, training‑free embodied navigation framework that wraps a multimodal LLM in an "Agent Harness" – a tool‑based protocol that validates planner actions against spatial evidence, tracks progress with hierarchical event memory, and maintains a persistent spatiotemporal graph for recovery. The system works for instruction‑following and object‑goal tasks, achieving 60.…
Hugging Face Daily Papersarxiv.orgYang Chen, Lirong Che, Zhenyu Huang8d1 minpaper
HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses arxiv.org
The paper presents HypoEvolve, a generational genetic algorithm that coordinates specialized LLM agents to iteratively propose, critique, and refine scientific hypotheses. On a drug‑repurposing benchmark across 34 cancer types, it outperforms six baselines, achieving a DepMap selectivity of 0.171 versus 0.115.
Hugging Face Daily Papersarxiv.orgJieyuan Liu, Mengzhou Hu, Jefferson Chen8d1 minpaper
Disentangling Representation Evolution in Transformers through Directional Decomposition arxiv.org
The paper decomposes transformer representation updates into parallel and perpendicular components, showing that parallel updates beyond the residual path are significant. Suppressing parallel updates during pretraining improves validation loss and downstream metrics.
Hugging Face Daily Papersarxiv.orgShwai He, Haichao Zhang, Shen Yan8d1 minpaper
VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention arxiv.org
VC-Attention introduces a training‑free low‑bit attention pipeline for diffusion transformers. It smooths value tensors via lightweight online clustering (V‑Smooth) and quantizes only the residual after subtracting block means, restoring the mean from the softmax row sum. It also replaces the FP32 softmax exponential with a fused FP8 cast (ExpCast‑FP8) that maps log‑scores directly to E4M3 probab…
Hugging Face Daily Papersarxiv.orgXingyang Li, Dongyun Zou, Shining Zhang8d1 minpaper
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement arxiv.org
ModularRSI proposes a contrastive, modular approach to evolve agent harnesses by independently updating five functional modules and aggregating evidence across 2,000 benchmark‑disjoint tasks. Experiments on TB2.0 and SWE‑Bench Verified show consistent gains on unseen tasks and cross‑model transfer.
Hugging Face Daily Papersarxiv.orgSiwei Wu, Jincheng Ren, Yizhi Li8d1 minpaper
The Router Within: Eliciting Native Skill Routing from a Frozen LLM arxiv.org
The paper introduces Gavel, a method that extracts a frozen LLM's internal routing signal via two trained linear maps, eliminating the need to embed skill descriptions in the prompt. Experiments on Qwen3‑32B show up to 13.4‑point improvements on task benchmarks and higher skill‑use accuracy compared to larger retrieval‑based systems.
Hugging Face Daily Papersarxiv.orgRuishuo Chen, Xun Wang, Yu Chen8d1 minpaper
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration arxiv.org
Decoy Direction Optimization (DDO) is a post‑hoc weight‑editing defense for open‑weight LLMs that injects a high‑magnitude nonlinear decoy into MLP neurons, corrupting contrastive estimators used by Refusal Feature Ablation (RFA) attacks. The paper proves a spectral bound on the effect, evaluates DDO on six model families (including Llama‑3‑8B‑Instruct), and shows <10 % attack success rate (ASR)…
Hugging Face Daily Papersarxiv.orgAashiq Muhamed, Mona T. Diab, Virginia Smith8d1 minpaper
Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition arxiv.org
Lightning Weave is a post‑training framework that composes specialist capabilities from separate models into one student via on‑policy distillation, improving both accuracy and token efficiency on math and code benchmarks.
Hugging Face Daily Papersarxiv.orgYecheng Wu, Song Han, Han Cai9d1 minpaper
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization arxiv.org
This paper introduces SpectralShift, a spectral reparameterization method for extending the context window of Gated DeltaNet (GDN) linear attention models. It reconfigures the decay spectrum by enhancing slow propagation and preserving fast-decaying modes, consistently improving long-context capabilities during continual pretraining.
Hugging Face Daily Papersarxiv.orgZian Liu, Yiwen Hu, Zican Dong9d1 minpaper
Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid?arxiv.org
The paper experiments with prompting six frontier LLM families using a school‑audience framing and finds their architectural design suggestions converge on a common pattern, while removing the framing yields diverse outputs. It highlights a possible shared design prior among models and introduces the term "epistemic jailbreak" for the loss of provenance in speculative answers.
Hugging Face Daily Papersarxiv.orgAfshin Khadangi9d1 minpaper
OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning arxiv.org
OmniHarness introduces a symbolic‑policy framework that extracts reusable procedural knowledge from multimodal LLM‑driven visual generation runs. By decoupling task logic from instance inputs, the system can instantiate, adapt, and compose policies for new visual tasks, using intermediate verification for on‑the‑fly refinement while keeping the underlying model frozen. Self‑directed practice task…
Hugging Face Daily Papersarxiv.orgXu Xu, Jinxiu Liu, Zhangbo Qiao9d1 minpaper
Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models arxiv.org
The paper reframes fine‑tuning of instruction‑tuned LLMs as a direction‑selection problem under a fixed behavioral‑drift budget, showing that the update direction, not magnitude, determines trade‑offs between target performance and capability preservation. In QA‑only fine‑tuning of Qwen‑3 models, layer‑selective probing finds effective directions that boost scientific reasoning and multilingual t…
Hugging Face Daily Papersarxiv.orgFei Yuan, Changjiang Gao, Yilei Tu10d1 minpaper
Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation arxiv.org
The paper shows that when specialist LLMs are trained only on QA pairs (no explicit reasoning supervision), their optimization implicitly selects a latent distribution of reasoning trajectories. By treating the distilled student as an agnostic probe—since it inherits only the sampled trajectories—the authors empirically demonstrate a strong correlation (across 27 specialist‑student pairs) between…
Hugging Face Daily Papersarxiv.orgYilei Tu, Zihao Li, Shaoxiong Ji10d1 minpaper
StepAudio 3 Realtime Technical Report arxiv.org
StepAudio 3 Realtime is an audio‑language foundation model that runs a continuous listen‑converse‑think‑act loop. It introduces Deep Perception for rich acoustic cue extraction, Seamless Duplex for handling pauses/back‑channels, and a Think‑While‑Speaking mechanism that lets the model reason in parallel with speech output. On benchmarks it scores 73.0 macro avg on StepAudioChat, 90.6 on MMSU, 98.…
Hugging Face Daily Papersarxiv.orgBin Lin, Bo Zhao, Boyang Zhang10d2 minpaper
Convergent Emergence of In-Context Learning Across Modalities arxiv.org
The paper proposes the Convergent Emergence Hypothesis that few‑shot in‑context learning (ICL) shares a common difficulty profile across domains. Using a unified task suite, the authors evaluate ICL on six modalities—language, genome, integer sequences, time‑series, images, and proteins—showing that paired‑mapping ICL emerges in all and that per‑task benefits correlate across five modalities, sup…
Hugging Face Daily Papersarxiv.orgNathan Breslow, Seungwook Han, Daniel Hyunsoo Lee10d1 minpaper
Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models arxiv.org
Latent Interface Training (LIT) first learns a goal‑conditioned action prior without visual input, then adds a pose‑supervised latent interface as the only visual conditioning path. Applied to several vision‑language‑action models, LIT cuts vision‑action shortcuts and lifts LIBERO‑Plus success by 3.9–10.7 points and real‑world task success by 13.3–16.7 points under distribution shifts.
Hugging Face Daily Papersarxiv.orgJianman Lin, Shailesh Shailesh, Zhongyi Luo11d1 minpaper
StepAudio 3 Gen Technical Report arxiv.org
StepAudio 3 Gen is a general‑purpose audio generation model that replaces diffusion with a discrete autoregressive generator over residual vector quantization tokens. Using a 16‑layer RVQ tokenizer and progressive pretraining, it reaches state‑of‑the‑art zero‑shot TTS and voice‑design performance while handling speech, vocals, sound effects, and music.
Hugging Face Daily Papersarxiv.orgBin Lin, Bo Zhao, Boyang Wang11d2 minpaperHN2
Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement arxiv.org
The paper introduces Generalized Agent Iteration (GAI), a formal framework that unifies classical iterative policy improvement (GPI) and recursive self‑improvement (RSI). GAI treats an agent as a set of modifiable components and models learning as a loop of evaluation and improvement. Two binary “dials”—whether the improvement mechanism is internal to the agent and whether the evaluation standard…
Hugging Face Daily Papersarxiv.orgHongyao Tang, Yi Ma, Pengyi Li11d1 minpaper
RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs arxiv.org
RelateAnything is a 53 M‑parameter model that predicts arbitrary textual relations between any supplied image regions, using a text‑embedding bank instead of a fixed classifier. Trained on a new 4.3 M‑relation dataset, it outperforms prior open‑vocab methods by 2.3‑3.5× mean recall while running in ~20 ms per frame.
Hugging Face Daily Papersarxiv.orgMaëlic Neau11d2 minpaper
SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image arxiv.org
The paper presents SNAP3D, a physics‑guided pipeline that converts a single image into a set of 3D parts that can be assembled without interpenetration. By using simulation‑driven connector placement and a new physics‑based evaluation, the method yields assemblies that are both geometrically accurate and stable enough for 3D printing.
Hugging Face Daily Papersarxiv.orgYu-Rou Tuan, Hao-Tang Tsui, Nicolas Ugrinovic11d1 minpaper
Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation arxiv.org
Benchmark Radar is a continuously updated database and search engine that aggregates AI benchmark papers, datasets, and scores from 37 sources into a searchable catalog. It offers a web dashboard, CLI, and analysis of benchmark saturation to help LLM developers find and compare evaluations.
Hugging Face Daily Papersarxiv.orgKoutian Wu, Junjie Zhou, Ergan Shang12d1 minpaper
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement arxiv.org
The paper defines recursive self‑improvement (RSI) for AI, introduces the Headroom‑Closed Index to expose current LLM limits, and proposes a staged roadmap toward full RSI. It surveys application scenarios and outlines practical challenges.
Hugging Face Daily Papersarxiv.orgYi Duan, Ying Liu, Zirui Tang12d1 minpaperHN3
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization arxiv.org
COBRA‑Skills uses a contextual‑bandit loop to selectively evaluate and evolve LLM agent skills, achieving better performance with roughly half the evaluation cost of prior methods. The framework works with limited examples and remains robust across different agent setups and even when the target model creates its own skills.
Hugging Face Daily Papersarxiv.orgPingchen Lu, Xiangyi Wang, Xiang Li12d1 minpaper
Towards a Deterministic Math Solver for Clinical Language Models arxiv.org
The paper proposes a Program‑Solve interface where LLMs emit Python code that a sandboxed executor runs, making arithmetic deterministic for clinical calculators. Experiments show the approach boosts a 32B model’s accuracy on a verified benchmark, but coverage and upstream extraction remain limiting factors.
Hugging Face Daily Papersarxiv.orgFelipe Ocampo Osorio, Sebastián Andrés Cajas Ordoñez, Maximin Lange13d1 minpaper
LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents arxiv.org
LLaDA‑UI is a 16.7 B‑parameter Mixture‑of‑Experts vision‑language model that uses block‑wise diffusion to generate GUI actions in parallel. It achieves state‑of‑the‑art performance on multiple GUI grounding and navigation benchmarks, beating larger Qwen models while keeping decoding latency low.
Hugging Face Daily Papersarxiv.orgZhangxuan Gu, Haoxing Chen, Qi Qin13d1 minpaper
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models arxiv.org
Feyospace‑v1 presents a data‑centric training pipeline for cyber‑security agents, combining five systems (Choulea, SkyReal, Hongzwang, PSBreakup, Kreator) to generate and verify 164 k long‑context trajectories across diverse exploit environments. The resulting checkpoints improve baseline performance by ~24% on CyberGym and achieve a 63% verified success rate, ranking top among similarly‑sized op…
Hugging Face Daily Papersarxiv.orgZongjie Li, Alan Z. W, John Nicolas J14d1 minpaper
Continual Learning Mechanisms Compose for Long-Horizon Memorization arxiv.org
The paper studies long‑horizon memorization where a language model must learn 100 tasks via continual fine‑tuning without retaining data or task IDs. By composing data, function, and weight anchors with merged LoRA, they boost final retention from 1.2% to 34.9%, a 28× improvement.
Hugging Face Daily Papersarxiv.orgZheyuan Zhang, Alvin Zhang, Daniel Khashabi15d1 minpaperHN2
Beyond Top-k Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents arxiv.org
Beyond Top‑k Skill Retrieval: Diversity‑Aware Skill Routing (DSR) applies a Determinantal Point Process with a query‑residual diversity kernel to rerank skill candidates, balancing relevance and redundancy. On the SkillRouter benchmark it raises recall and full‑coverage, especially for multi‑skill queries, showing that skill routing benefits from set‑selection rather than independent ranking.
Hugging Face Daily Papersarxiv.orgWang Wei, Tiankai Yang, Samyadeep Basu17d1 minpaper
DataFlex-RL: An Evaluation Platform for RLVR Data Policies arxiv.org
The paper introduces DataFlex‑RL, a platform to benchmark how different data‑selection policies affect reinforcement‑learning‑with‑verifiable‑rewards training. Across extensive experiments on Qwen2.5‑7B and Llama‑3.1‑8B, uniform sampling is the only method that consistently improves performance, and no alternative policy yields a statistically significant gain.
Hugging Face Daily Papersarxiv.orgHao Liang, Mingrui Chen, Hengyi Feng17d1 minpaper
Online Learning with LLM Experts from Limited Feedback arxiv.org
The paper models prompt routing to multiple LLM experts as a bandit problem with limited feedback and proposes algorithms that achieve sublinear regret in both full‑information and bandit settings. Experiments demonstrate that the methods learn effective routing strategies across diverse LLMs using only a small feedback budget.
Hugging Face Daily Papersarxiv.orgWang Wei, Soumyabrata Pal, Koyel Mukherjee17d2 minpaper