Good Papers

Showing papers from Vector Institute Show all papers

89%Must read
?Must readVote to see the score
arXivU TorontoVector InstituteThomson ReutersReward models & LLM-as-a-judge

Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers

LLM scorers with equal ranking quality make unstable threshold and preference decisions under candidate reordering, and order-consistency fine-tuning fixes it without harming quality.

Markus Frohmann, Mahdiyar Alavi, Elizabeth Lingg, Navid Rekabsaz

Published Aug 27, 2026 · 0 citations · ▲ 17 on Hugging Face · Code ★ 2

– ReadersNo votes yet
16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it
lenient 5/5
medium 9/10
strict 2/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Vector InstituteCarletonDalhousieUBC / VectorU Guelph / Vector InstituteLLM pretraining & scaling laws

Self-Distillation of Hidden Layers for Masked Self-Supervised Representation Learning

Scott C. Lowe, Anthony Fuller, Sageev Oore, Evan Shelhamer and 1 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Vector InstituteU TorontoETH ZurichDepartment of Computer Science, Max Planck Institute for IntelliLLM evaluation & benchmarks

SuperSycophantic: Stress-Testing Frontier LLMs from Single- to Multi-Turn Sycophancy

Terry J Zhang, Oscar S Yasunaga, Wenyuan Jiang, Jessica Bo and 7 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Seoul NationalVector InstituteKoreaOffline RL

MINT: Meeting-time INdicators for Truncation in Multi-Step Off-Policy RL

Seungyub Han, Taehyun Cho, Dohyeong Kim, Kyungjae Lee and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U British ColumbiaZhejiangStanfordVector InstituteUBC | Vector Institute | GoogleSpeech synthesis

RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models

Ruinan Jin, Xinting Liao, Hanlin Yu, Deval Pandya and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Instituto Superior TecnicoVector InstituteU LisbonInstituto de TelecomunicacoesRIKEN AIPBayesian & probabilistic methods

The Bayesian Learning Rule Beyond KL Geometry

SOPHIA SKLAVIADIS, Wu Lin, Mario Figueiredo, André Martins and 2 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026McMasterVector InstituteDepartment of Computer Science, Carnegie MellonMPI for Intelligent Systems, TübAgent benchmarks & environments

AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment

Eric Zhang, Terry J Zhang, Chijioke Ugwuanyi, Jerick Shi and 2 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
83%Must read
?Must readVote to see the score
NeurIPS 2026U California, RiversideNew YorkUCRVector InstituteU California RiversideLLM pretraining & scaling laws

Discrete Stochastic Localization for Non-autoregressive Generation

Discrete stochastic localization uses unit-sphere embeddings with SNR-invariant denoisers to enable flexible continuous-state non-autoregressive generation with improved fidelity and hybrid sampling.

Yunshu Wu, Jiayi Cheng, Longxuan YU, Partha Thakuria and 3 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it
lenient 2/5
medium 9/10
strict 2/5
80%Must read
?Must readVote to see the score
NeurIPS 2026Vector InstituteU AlbertaYorkQueen'sYork University; Vector InstitutLLM evaluation & benchmarks

Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models

An automated framework generates fine-grained, contamination-robust benchmarks from textbooks that expose model differences missed by existing tests.

Mohammed Saidul Islam, Arash Afkanpour, Negin Baghbanzadeh, Farnaz Kohankhaki and 4 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 0/5
80%Must read
?Must readVote to see the score
NeurIPS 2026Seoul NationalVector InstituteMicrosoft ResearchVideo understanding

Why Latent Actions Fail, and How to Prevent It

Standard reconstruction in latent action models encodes exogenous future state, but endogenous representations and action supervision prevent this failure.

Jung Min Lee, Taehyun Cho, Li Zhao, Jungwoo Lee

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 2/5
88%Must read
?Must readVote to see the score
NeurIPS 2026NorthwesternVector InstituteLLM evaluation & benchmarks

TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting

TEMPO trains LLMs via mode-separated reinforcement learning to eliminate post-cutoff knowledge leakage in temporal backtesting, cutting leakage to 0.6-3.7% while improving task performance up to 13%.

Zeyu Zhang, Bradly Stadie

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 15 of 20 reviewers recommend it
lenient 5/5
medium 9/10
strict 1/5
89%Must read
?Must readVote to see the score
NeurIPS 2026EuroSafeAIETHZ - ETH ZurichMATS ResearchMPI for Intelligent Systems, TübVector InstituteAI oversight & deception

GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory

GT-HarmBench evaluates 15 frontier AI models on 1,535 multi-agent game-theoretic risk scenarios, finding 38% failure at socially beneficial actions and up to 18% improvement via interventions.

Pepijn Cobben, Xuanqiang A Huang, Thao Pham, Isabel Dahlgren and 3 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it
lenient 5/5
medium 9/10
strict 2/5
83%Must read
?Must readVote to see the score
NeurIPS 2026York University and Vector InstiYorkVector InstituteDalhousieYork University; Vector InstitutLLM evaluation & benchmarks

Towards Understanding and Measuring Cognitive Atrophy in LLM Behaviour

Cognitive atrophy is formalized as a process-level behavioral measure in AI mental-health support, with a 1,576-conversation benchmark showing LLMs consistently exhibit moderate-to-high atrophy-aligned directive and validation patterns.

Abeer Badawi, Moyosoreoluwa Olatosi, Negin Baghbanzadeh, Laleh Seyyed-Kalantari and 4 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it
lenient 5/5
medium 6/10
strict 2/5
83%Must read
?Must readVote to see the score
NeurIPS 2026Vector InstituteUBC and Vector InstituteU TorontoYork University and Vector InstiNVIDIA, Arc Institute, Vector InMultimodal reasoning

OpenMedReason: Scientific Reasoning Supervision for Medical Vision–Language Models

OpenMedReason is a 450K-instance open medical reasoning dataset derived from scientific articles that improves LVLM diagnostic accuracy by 20% and enhances perception, knowledge, and reasoning.

Negin Baghbanzadeh, Pritam Sarkar, Michael Colacci, Abeer Badawi and 5 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it
lenient 5/5
medium 5/10
strict 3/5