Sumi is an openly released 7B parameter uniform diffusion language model pretrained from scratch on 1.5T tokens that matches autoregressive models on several benchmarks.
super hub Mixed citations
gpt-oss-120b & gpt-oss-20b Model Card
Mixed citation behavior. Most common role is background (41%).
433
Pith papers citing it
Background
41% of classified citations
abstract
We present gpt-oss-120b and gpt-oss-20b, two open-weight reasoning models that push the frontier of accuracy and inference cost. The models use an efficient mixture-of-expert transformer architecture and are trained using large-scale distillation and reinforcement learning. We optimize the models to have strong agentic capabilities (deep research browsing, python tool use, and support for developer-provided functions), all while using a rendered chat format that enables clear instruction following and role delineation. Both models achieve strong results on benchmarks ranging from mathematics, coding, and safety. We release the model weights, inference implementations, tool environments, and tokenizers under an Apache 2.0 license to enable broad use and further research.
hub tools
citation-role summary
background 33
baseline 16
method 16
other 6
dataset 5
citation-polarity summary
claims ledger
- abstract We present gpt-oss-120b and gpt-oss-20b, two open-weight reasoning models that push the frontier of accuracy and inference cost. The models use an efficient mixture-of-expert transformer architecture and are trained using large-scale distillation and reinforcement learning. We optimize the models to have strong agentic capabilities (deep research browsing, python tool use, and support for developer-provided functions), all while using a rendered chat format that enables clear instruction following and role delineation. Both models achieve strong results on benchmarks ranging from mathematics,
authors
co-cited works
representative citing papers
TW-LegalBench evaluates 13 LLMs on over 30,000 Taiwanese legal tasks from exams and judgments, showing top models pass lawyer thresholds but struggle with exact statute citations.
UltraEP is the first exact-load real-time expert balancer for large-EP MoE training and serving on rack-scale nodes, reaching 94.3% of ideal throughput and 1.49x over no-balancing.
RobotValues is a benchmark of 10K value-conflict scenarios that reveals VLMs default to safety and accommodation while failing to follow instructions to prioritize other values 80% of the time.
Presents the first fully open pipeline for clinical LLMs by unifying eight public QA datasets with three clinician-vetted synthetic extensions and applying it to five base models to achieve benchmark gains while maintaining auditability.
MathAtlas is the first large-scale benchmark for autoformalizing graduate mathematics, where even strong models reach only 9.8% correctness on theorem statements and drop to 2.6% on the hardest dependency-deep subset.
LLMs lack temporal awareness of medical knowledge, showing gradual performance decline on up-to-date facts, much lower accuracy on historical knowledge (25-54% relative), and inconsistent year-to-year predictions.
Sieve dynamically schedules MoE experts across GPU and PIM hardware to handle bimodal token distributions, achieving 1.3x to 1.6x gains in throughput and interactivity over static prior PIM systems on three large models.
Soohak is a 439-problem mathematician-curated benchmark where frontier LLMs reach at most 30.4% on research math challenges and no model exceeds 50% on refusal for ill-posed problems.
MathConstraint generates scalable, automatically verifiable combinatorial problems where LLMs achieve 18.5-66.9% accuracy without tools but roughly double that with solver access.
IRIS-14B is the first LLM trained explicitly for GIMPLE-to-LLVM IR translation and outperforms much larger models by up to 44 percentage points on real-world C code.
RoundPipe achieves near-zero-bubble pipeline parallelism for LLM training on consumer GPUs by dynamically dispatching computation stages round-robin, yielding 1.48-2.16x speedups and enabling 235B model fine-tuning on 8x RTX 4090.
InfiniteScienceGym procedurally generates unbounded scientific repositories with exact ground-truth QA pairs to benchmark LLMs on data reasoning, abstention, and tool use without static datasets.
Large language models display the identifiable victim effect at roughly twice the human baseline, strongly amplified by instruction tuning and chain-of-thought prompting but inverted by reasoning-specialized models.
Tessera performs kernel-granularity disaggregation on heterogeneous GPUs, achieving up to 2.3x throughput and 1.6x cost efficiency gains for large model inference while generalizing beyond prior methods.
The SDE benchmark shows LLMs lag on scientific discovery tasks relative to general science tests, with diminishing scaling returns and shared weaknesses across models.
SpeechCombine produces instruction-following SLMs via speech pre-training followed by direct weight combination with the text LLM instruction delta, without any speech instruction tuning.
OpenSafeIntent benchmark shows models fail to calibrate safety across intent shifts in matched dual-use prompts, indicating current evaluations are insufficient.
A 0.6B LM with length-aware attention adjustments performs competitive in-context retrieval at million-token scale on MS MARCO, NQ, and LIMIT benchmarks.
LLM-generated research ideas cluster more around bridge-like opportunities and synthesis methods than the broader distribution seen in human papers.
ELDR reduces median TPOT by 5.9-13.9% in PD-disaggregated MoE serving via expert signatures from prefill, K-means partitioning, and locality-band routing with KV-co-indexed signature cache.
Introduces GenAI agent framework for auditing personalization algorithms via synthetic accounts with fixed personas, applied to X post-2024 election showing amplification of toxic and right-leaning content varying by ideology.
SABER-Math is an automated benchmark for mathematical IR that uses LLM summaries, topic similarities, and preference tournaments on 283K problems to create reranking tasks, showing embedding models outperform baselines but struggle in symbol-heavy areas and that MTEB does not predict math performanc
LLM agents often fail to abstain at the right time in uncertain multi-turn tasks, and the CONVOLVE context engineering method raises timely abstention rates on WebShop from 26.7 to 57.4 without parameter updates.
citing papers explorer
-
REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak
Reflector internalizes step-wise self-reflection in LLMs via teacher-guided SFT then RL with outcome and validity rewards, claiming over 90% defense success against indirect jailbreaks plus utility gains like 5.85% on GSM8K.
-
Occupational Prompting Reveals Cultural Bias in Large Language Models
Occupational prompting of open-weight LLMs elicits structured value patterns in Inglehart-Welzel cultural space, extending prior nationality-based cultural bias evaluations.
-
Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation
MOTAB is a new distillation pipeline that monitors on-policy student trajectories and backtracks with teacher intervention to mitigate dual exposure biases, improving reasoning performance by about 3%.
-
Query-Conditioned Knowledge Alignment for Reliable Cross-System Medical Reasoning
QCEA reformulates entity alignment as a query-conditioned ranking task with semantic encoding, graph learning, and direction-aware transformation to handle context-dependent, asymmetric correspondences in medical knowledge graphs.
-
The Misattribution Gap: When Memory Poisoning Looks Like Model Failure in Agentic AI Systems
Memory poisoning via lost-provenance documents in agent memory stores creates agent misconduct that safety systems misattribute to model failure; the paper defines Semantic Norm Drift, releases a benchmark, and proposes a new testing method plus a defense.
-
Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
Pion is an optimizer that preserves the singular values of weight matrices in LLM training by applying orthogonal equivalence transformations.
-
Evaluating the False Trust Engendered by LLM Explanations
LLM reasoning traces and post-hoc explanations increase false trust in incorrect predictions, whereas contrastive dual explanations enhance users' ability to distinguish correct from incorrect AI outputs.
-
Speech-based Psychological Crisis Assessment using LLMs
LLM system with paralinguistic cue injection and auxiliary reasoning training reaches 0.802 macro F1 and 0.805 accuracy on three-class speech-based crisis level classification under 5-fold cross-validation.
-
A Prompt-Aware Structuring Framework for Reliable Reuse of AI-Generated Content in the Agentic Web
A framework structures AI-generated content with prompt-aware metadata and verifiable credentials to support reliable assessment and reuse by agents.
-
Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs
EngGPT2MoE-16B-A3B matches or exceeds other Italian open-source LLMs on most international benchmarks while remaining competitive on ITALIC, though it trails some top international models.
-
LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
LensVLM trains VLMs to scan compressed rendered text images and selectively expand task-relevant regions, achieving 4.3x compression with near full-text accuracy and outperforming baselines up to 10.1x on text QA benchmarks.
-
Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use
A server-side architecture with policy-aware ingestion and ABAC-based retrieval gating prevents cross-tenant data leakage in multitenant enterprise RAG and agent systems.
-
An Evaluation of Chat Safety Moderations in Roblox
Roblox's automated chat moderation fails to catch numerous unsafe messages involving grooming, sexualization of minors, bullying, violence, self-harm, and sensitive information sharing, with users evading detection through various techniques.
-
Evaluating Retrieval-Augmented Generation for Explainable Malware Analysis
RAG frequently degrades LLM malware explanations when structured VirusTotal input is already available by introducing irrelevant context and narrative noise.
-
KG-First, LLM-Fallback: A Hybrid Microservice for Grounded Skill Search and Explanation
SkillGraph-Service builds a provenance-preserving knowledge graph from multiple competency frameworks and achieves nDCG@5 above 0.94 with sub-200 ms latency via KG-first hybrid retrieval and constrained LLM explanations.
-
Colinearity Decay: Training Quantization-Friendly ViTs with Outlier Decay
Colinearity-Decay regularizer trains ViTs that maintain or improve full-precision accuracy while delivering higher accuracy after low-bit quantization on ImageNet and COCO tasks.
-
Tandem: Riding Together with Large and Small Language Models for Efficient Reasoning
Tandem lets a large model supply compact strategic guidance to a small model for reasoning tasks, achieving similar or better performance at about 40 percent lower cost through adaptive early stopping.
-
LayerBoost: Layer-Aware Attention Reduction for Efficient LLMs
LayerBoost selectively replaces or removes attention in non-critical transformer layers to cut inference latency up to 68% while recovering quality via brief distillation.
-
Looking Into the Past: Eye Movements Characterize Elements of Autobiographical Recall in Interviews with Holocaust Survivors
Eye movements during Holocaust survivor interviews vary by episodic, semantic, affective and temporal memory dimensions, with pre-onset gaze sufficient to predict sentence temporal context.
-
OptiMat Alloys: a FAIR, living database of multi-principal element alloys enabled by a conversational agent
OptiMat Alloys is a conversational AI system that maintains a living FAIR database of multi-principal element alloy calculations and enables natural-language, on-demand computations with built-in uncertainty checks.
-
LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues
LePREC combines LLM-generated analytical QA factors with sparse linear classification to achieve 30-40% better precision than pure LLMs in identifying relevant legal issues from court cases.
-
Do Emotions Influence Moral Judgment in Large Language Models?
Inducing emotions shifts LLM moral judgments in a valence-dependent manner that reverses decisions in up to 20% of cases and does not appear in humans.
-
Exploring Concreteness Through a Figurative Lens
LLMs compress concreteness into a consistent 1D direction in mid-to-late layers that separates literal from figurative noun uses and supports efficient classification plus steering.
-
Heterogeneity in Formal Linguistic Competence of Language Models: Is Data the Real Bottleneck?
Injecting 1% synthetic data targeting specific constructions during pre-training of GPT-2 Small boosts performance on 8 of 9 weakest BLiMP paradigms (e.g., only_npi_scope from 20.9% to 69.4%), while aggregate performance holds or improves, with one resistant case.
-
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
Nemotron 3 Super is an open 120B hybrid Mamba-Attention MoE model with new LatentMoE architecture and MTP layers that matches accuracy of similar models while delivering up to 7.5x higher inference throughput.
-
Beyond Imperfect Alternatives with Rulemapping: A Neuro-Symbolic Case Study on Online Hate Speech
Rulemapping uses expert symbolic scaffolds to constrain LLMs, raising precision on §130(1) German hate-speech classification from 0.34-0.49 to 0.80-0.86 while preserving recall of 0.82-0.89.
-
Decomposing the Delta: What Do Models Actually Learn from Preference Pairs?
Larger differences in generator capability between chosen and rejected reasoning traces improve out-of-domain performance, while filtering pairs by sample-level quality deltas enables more data-efficient training.
-
PIArena: A Platform for Prompt Injection Evaluation
PIArena provides a unified evaluation platform for prompt injection attacks and defenses, featuring a new adaptive attack that reveals major weaknesses in existing protections.
-
A Decomposition Perspective to Long-context Reasoning for LLMs
Decomposing long-context reasoning into atomic skills, synthesizing targeted pseudo-datasets, and applying RL improves LLM performance on long-context benchmarks by an average of 7.7%.
-
Does a Global Perspective Help Prune Sparse MoEs Elegantly?
GRAPE is a global redundancy-aware pruning strategy for sparse MoEs that dynamically allocates pruning budgets across layers and improves average accuracy by 1.40% over the best local baseline across tested models and settings.
-
Train the Trainers -- An Agentic AI Framework for Peer-Based Mental Health Support in Battlefield Environments
The paper introduces an agentic AI platform to train and support recovered soldiers as peer facilitators providing mental health triage and interventions in austere battlefield environments.
-
MiMo-V2-Flash Technical Report
MiMo-V2-Flash is a 309B/15B MoE model trained on 27T tokens with hybrid attention and multi-teacher on-policy distillation that matches larger models like DeepSeek-V3.2 while enabling 2.6x faster decoding via repurposed MTP layers.
-
NVIDIA Nemotron 3: Efficient and Open Intelligence
NVIDIA releases the Nemotron 3 model family with hybrid Mamba-Transformer architecture, LatentMoE, NVFP4 training, MTP layers, and multi-environment RL post-training for reasoning and agentic tasks.
-
Benchmarking and Adapting On-Device LLMs for Clinical Decision Support
Fine-tuned on-device LLMs achieve up to 87.9% diagnostic accuracy on clinical tasks, approaching GPT-5.1 at 89.4% while remaining smaller and local.
-
Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Framework
Matrix provides a peer-to-peer multi-agent system for synthetic data generation that scales to tens of thousands of workflows and delivers 2-15x higher throughput than centralized designs without quality loss.
-
Food4All: A Multi-Agent Framework for Real-time Free Food Discovery with Integrated Nutritional Metadata
Food4All is a multi-agent framework combining heterogeneous data aggregation, lightweight reinforcement learning for accessibility and nutrition, and an online feedback loop to provide real-time, context-aware free food discovery with nutritional metadata.
-
Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models
GenCluster scales test-time compute via large-scale generation, behavioral clustering, ranking, and round-robin submission to achieve IOI gold medal performance with the open-weight gpt-oss-120b model.
-
DeepPrune: Parallel Scaling without Inter-trace Redundancy
DeepPrune prunes redundant parallel CoT traces via a judge model for equivalence prediction from partial traces plus online greedy clustering, delivering 65-88% token savings with accuracy within 3 points on AIME and GPQA benchmarks.
-
Measuring Competency, Not Performance: Item-Aware Evaluation Across Medical Benchmarks
MedIRT applies Item Response Theory to medical LLM benchmarks to separate latent competency from item difficulty and discrimination, producing more stable rankings and revealing domain heterogeneity than accuracy alone.
-
RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems
RECAP is an inference-time framework using cognitive appraisal theory to enhance emotional alignment and transparency in medical dialogue systems across model scales.
-
SCAN: Structured Capability Assessment and Navigation for LLMs
SCAN is a framework for fine-grained LLM capability assessment via automatic taxonomy construction from queries, query synthesis for coverage, visualization tools, and a PC2-enhanced LLM-as-a-judge method, applied to 21 models showing intra-family variations.
-
On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain
Moderate pruning of MoE models preserves in-domain biomedical utility and reliability but both degrade rapidly in cross-domain settings and at extreme pruning ratios.
-
MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers
MATCH augments sparsified attention with an efficient in-context retrieval system to boost performance on long-range recall tasks in transformers.
-
Fine-Tuning Large Language Models for Quantum Reasoning
Supervised fine-tuning on gate-by-gate quantum simulation traces allows LLMs to achieve near-perfect accuracy in predicting quantum measurement outcomes, with added GRPO improving generalization to larger qubit counts.
-
SuCo: Sufficiency-guided Continuous Adaptive Reasoning
SuCo defines minimal sufficient CoT and applies a two-stage fine-tuning plus RL framework to enable continuous adaptive reasoning control, claiming gains in both accuracy and token efficiency on math, code, and science tasks.
-
Sim2Schedule: A Simulator-Guided LLM Framework for Autonomous Open-Pit Mine Scheduling
Simulator-constrained LLM recovers 94-99% of MILP optimal NPV for mine scheduling while scaling linearly.
-
Does Normalization Choice Matter for Causal Large Time-Series Models?
Normalization choice significantly influences training convergence and forecasting performance in causal large time-series models.
-
Supervision versus Demonstration-Based In-Context Learning for Multiword Expression Classification
On a controlled Turkish dataset of 147 examples, few-shot prompting lets some LLMs match or beat a supervised BERT baseline for LVC detection, though results are highly sensitive to prompt design.
-
Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis
HAZDIAL shows structured agentic dialogue improves LLM-based hazard identification quality over single-pass methods on a curated golden dataset using classification and dialogue metrics.
-
LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning
LongAttnComp adapts attention-based context compression with token-level chunking, positional reordering, and two-stage fine-tuning to match full-context performance on InfiniteBench Code-Debug and improve multi-document reasoning on LongBench v2 across model families.